diff options
Diffstat (limited to 'pkg_resources')
| -rw-r--r-- | pkg_resources/__init__.py | 303 | ||||
| -rw-r--r-- | pkg_resources/_vendor/appdirs.py | 552 | ||||
| -rwxr-xr-x[-rw-r--r--] | pkg_resources/_vendor/pyparsing.py | 3478 | ||||
| -rw-r--r-- | pkg_resources/_vendor/vendored.txt | 3 | ||||
| -rw-r--r-- | pkg_resources/extern/__init__.py | 4 | ||||
| -rw-r--r-- | pkg_resources/tests/test_markers.py | 1 | ||||
| -rw-r--r-- | pkg_resources/tests/test_pkg_resources.py | 8 | ||||
| -rw-r--r-- | pkg_resources/tests/test_resources.py | 91 |
8 files changed, 3476 insertions, 964 deletions
diff --git a/pkg_resources/__init__.py b/pkg_resources/__init__.py index 2eab8230..37bf1482 100644 --- a/pkg_resources/__init__.py +++ b/pkg_resources/__init__.py @@ -1,3 +1,5 @@ +# coding: utf-8 + """ Package resource API -------------------- @@ -65,6 +67,7 @@ try: except ImportError: importlib_machinery = None +from pkg_resources.extern import appdirs from pkg_resources.extern import packaging __import__('pkg_resources.extern.packaging.version') __import__('pkg_resources.extern.packaging.specifiers') @@ -155,7 +158,7 @@ class _SetuptoolsVersionMixin(object): # pad for numeric comparison yield part.zfill(8) else: - yield '*'+part + yield '*' + part # ensure that alpha/beta/candidate are before final yield '*final' @@ -209,36 +212,44 @@ def parse_version(v): _state_vars = {} + def _declare_state(vartype, **kw): globals().update(kw) _state_vars.update(dict.fromkeys(kw, vartype)) + def __getstate__(): state = {} g = globals() for k, v in _state_vars.items(): - state[k] = g['_sget_'+v](g[k]) + state[k] = g['_sget_' + v](g[k]) return state + def __setstate__(state): g = globals() for k, v in state.items(): - g['_sset_'+_state_vars[k]](k, g[k], v) + g['_sset_' + _state_vars[k]](k, g[k], v) return state + def _sget_dict(val): return val.copy() + def _sset_dict(key, ob, state): ob.clear() ob.update(state) + def _sget_object(val): return val.__getstate__() + def _sset_object(key, ob, state): ob.__setstate__(state) + _sget_none = _sset_none = lambda *args: None @@ -265,9 +276,10 @@ def get_supported_platform(): pass return plat + __all__ = [ # Basic resource access and distribution/entry point discovery - 'require', 'run_script', 'get_provider', 'get_distribution', + 'require', 'run_script', 'get_provider', 'get_distribution', 'load_entry_point', 'get_entry_map', 'get_entry_info', 'iter_entry_points', 'resource_string', 'resource_stream', 'resource_filename', @@ -311,10 +323,12 @@ __all__ = [ 'run_main', 'AvailableDistributions', ] + class ResolutionError(Exception): """Abstract base for dependency resolution errors""" + def __repr__(self): - return self.__class__.__name__+repr(self.args) + return self.__class__.__name__ + repr(self.args) class VersionConflict(ResolutionError): @@ -391,6 +405,8 @@ class DistributionNotFound(ResolutionError): class UnknownExtra(ResolutionError): """Distribution doesn't have an "extra feature" of the given name""" + + _provider_factories = {} PY_MAJOR = sys.version[:3] @@ -400,6 +416,7 @@ SOURCE_DIST = 1 CHECKOUT_DIST = 0 DEVELOP_DIST = -1 + def register_loader_type(loader_type, provider_factory): """Register `provider_factory` to make providers for `loader_type` @@ -409,6 +426,7 @@ def register_loader_type(loader_type, provider_factory): """ _provider_factories[loader_type] = provider_factory + def get_provider(moduleOrReq): """Return an IResourceProvider for the named module or requirement""" if isinstance(moduleOrReq, Requirement): @@ -421,6 +439,7 @@ def get_provider(moduleOrReq): loader = getattr(module, '__loader__', None) return _find_adapter(_provider_factories, loader)(module) + def _macosx_vers(_cache=[]): if not _cache: version = platform.mac_ver()[0] @@ -436,9 +455,11 @@ def _macosx_vers(_cache=[]): _cache.append(version.split('.')) return _cache[0] + def _macosx_arch(machine): return {'PowerPC': 'ppc', 'Power_Macintosh': 'ppc'}.get(machine, machine) + def get_build_platform(): """Return this platform's string for platform-specific distributions @@ -464,6 +485,7 @@ def get_build_platform(): pass return plat + macosVersionString = re.compile(r"macosx-(\d+)\.(\d+)-(.*)") darwinVersionString = re.compile(r"darwin-(\d+)\.(\d+)\.(\d+)-(.*)") # XXX backward compat @@ -477,7 +499,7 @@ def compatible_platforms(provided, required): XXX Needs compatibility checks for Linux and other unixy OSes. """ - if provided is None or required is None or provided==required: + if provided is None or required is None or provided == required: # easy case return True @@ -524,9 +546,11 @@ def run_script(dist_spec, script_name): ns['__name__'] = name require(dist_spec)[0].run_script(script_name, ns) + # backward compatibility run_main = run_script + def get_distribution(dist): """Return a current distribution object for a Requirement or string""" if isinstance(dist, six.string_types): @@ -537,14 +561,17 @@ def get_distribution(dist): raise TypeError("Expected string, Requirement, or Distribution", dist) return dist + def load_entry_point(dist, group, name): """Return `name` entry point of `group` for `dist` or raise ImportError""" return get_distribution(dist).load_entry_point(group, name) + def get_entry_map(dist, group=None): """Return the entry point map for `group`, or the full entry map""" return get_distribution(dist).get_entry_map(group) + def get_entry_info(dist, group, name): """Return the EntryPoint object for `group`+`name`, or ``None``""" return get_distribution(dist).get_entry_info(group, name) @@ -732,7 +759,7 @@ class WorkingSet(object): for key in self.entry_keys[item]: if key not in seen: - seen[key]=1 + seen[key] = 1 yield self.by_key[key] def add(self, dist, entry=None, insert=True, replace=False): @@ -752,8 +779,8 @@ class WorkingSet(object): if entry is None: entry = dist.location - keys = self.entry_keys.setdefault(entry,[]) - keys2 = self.entry_keys.setdefault(dist.location,[]) + keys = self.entry_keys.setdefault(entry, []) + keys2 = self.entry_keys.setdefault(dist.location, []) if not replace and dist.key in self.by_key: # ignore hidden distros return @@ -947,11 +974,17 @@ class WorkingSet(object): return needed - def subscribe(self, callback): - """Invoke `callback` for all distributions (including existing ones)""" + def subscribe(self, callback, existing=True): + """Invoke `callback` for all distributions + + If `existing=True` (default), + call on all existing ones, as well. + """ if callback in self.callbacks: return self.callbacks.append(callback) + if not existing: + return for dist in self: callback(dist) @@ -1027,7 +1060,7 @@ class Environment(object): is returned. """ return (self.python is None or dist.py_version is None - or dist.py_version==self.python) \ + or dist.py_version == self.python) \ and compatible_platforms(dist.platform, self.platform) def remove(self, dist): @@ -1232,7 +1265,7 @@ class ResourceManager: extract, as it tracks the generated names for possible cleanup later. """ extract_path = self.extraction_path or get_default_cache() - target_path = os.path.join(extract_path, archive_name+'-tmp', *names) + target_path = os.path.join(extract_path, archive_name + '-tmp', *names) try: _bypass_ensure_directory(target_path) except: @@ -1326,49 +1359,18 @@ class ResourceManager: """ # XXX -def get_default_cache(): - """Determine the default cache location - This returns the ``PYTHON_EGG_CACHE`` environment variable, if set. - Otherwise, on Windows, it returns a "Python-Eggs" subdirectory of the - "Application Data" directory. On all other systems, it's "~/.python-eggs". +def get_default_cache(): """ - try: - return os.environ['PYTHON_EGG_CACHE'] - except KeyError: - pass + Return the ``PYTHON_EGG_CACHE`` environment variable + or a platform-relevant user cache dir for an app + named "Python-Eggs". + """ + return ( + os.environ.get('PYTHON_EGG_CACHE') + or appdirs.user_cache_dir(appname='Python-Eggs') + ) - if os.name!='nt': - return os.path.expanduser('~/.python-eggs') - - # XXX this may be locale-specific! - app_data = 'Application Data' - app_homes = [ - # best option, should be locale-safe - (('APPDATA',), None), - (('USERPROFILE',), app_data), - (('HOMEDRIVE','HOMEPATH'), app_data), - (('HOMEPATH',), app_data), - (('HOME',), None), - # 95/98/ME - (('WINDIR',), app_data), - ] - - for keys, subdir in app_homes: - dirname = '' - for key in keys: - if key in os.environ: - dirname = os.path.join(dirname, os.environ[key]) - else: - break - else: - if subdir: - dirname = os.path.join(dirname, subdir) - return os.path.join(dirname, 'Python-Eggs') - else: - raise RuntimeError( - "Please set the PYTHON_EGG_CACHE enviroment variable" - ) def safe_name(name): """Convert an arbitrary string to a standard distribution name @@ -1386,7 +1388,7 @@ def safe_version(version): # normalize the version return str(packaging.version.Version(version)) except packaging.version.InvalidVersion: - version = version.replace(' ','.') + version = version.replace(' ', '.') return re.sub('[^A-Za-z0-9.]+', '-', version) @@ -1404,7 +1406,7 @@ def to_filename(name): Any '-' characters are currently replaced with '_'. """ - return name.replace('-','_') + return name.replace('-', '_') def invalid_marker(text): @@ -1462,16 +1464,11 @@ class NullProvider: def has_metadata(self, name): return self.egg_info and self._has(self._fn(self.egg_info, name)) - if sys.version_info <= (3,): - def get_metadata(self, name): - if not self.egg_info: - return "" - return self._get(self._fn(self.egg_info, name)) - else: - def get_metadata(self, name): - if not self.egg_info: - return "" - return self._get(self._fn(self.egg_info, name)).decode("utf-8") + def get_metadata(self, name): + if not self.egg_info: + return "" + value = self._get(self._fn(self.egg_info, name)) + return value.decode('utf-8') if six.PY3 else value def get_metadata_lines(self, name): return yield_lines(self.get_metadata(name)) @@ -1491,7 +1488,7 @@ class NullProvider: return [] def run_script(self, script_name, namespace): - script = 'scripts/'+script_name + script = 'scripts/' + script_name if not self.has_metadata(script): raise ResolutionError("No script named %r" % script_name) script_text = self.get_metadata(script).replace('\r\n', '\n') @@ -1507,7 +1504,7 @@ class NullProvider: cache[script_filename] = ( len(script_text), 0, script_text.split('\n'), script_filename ) - script_code = compile(script_text, script_filename,'exec') + script_code = compile(script_text, script_filename, 'exec') exec(script_code, namespace, namespace) def _has(self, path): @@ -1537,6 +1534,7 @@ class NullProvider: "Can't perform this operation for loaders without 'get_data()'" ) + register_loader_type(object, NullProvider) @@ -1552,7 +1550,7 @@ class EggProvider(NullProvider): # of multiple eggs; that's why we use module_path instead of .archive path = self.module_path old = None - while path!=old: + while path != old: if _is_unpacked_egg(path): self.egg_name = os.path.basename(path) self.egg_info = os.path.join(path, 'EGG-INFO') @@ -1561,6 +1559,7 @@ class EggProvider(NullProvider): old = path path, base = os.path.split(path) + class DefaultProvider(EggProvider): """Provides access to package resources in the filesystem""" @@ -1586,6 +1585,7 @@ class DefaultProvider(EggProvider): type(None)) register_loader_type(loader_cls, cls) + DefaultProvider._register() @@ -1600,6 +1600,7 @@ class EmptyProvider(NullProvider): def __init__(self): pass + empty_provider = EmptyProvider() @@ -1678,7 +1679,7 @@ class ZipProvider(EggProvider): def __init__(self, module): EggProvider.__init__(self, module) - self.zip_pre = self.loader.archive+os.sep + self.zip_pre = self.loader.archive + os.sep def _zipinfo_name(self, fspath): # Convert a virtual filename (full path to file) into a zipfile subpath @@ -1692,9 +1693,9 @@ class ZipProvider(EggProvider): def _parts(self, zip_path): # Convert a zipfile subpath into an egg-relative path part list. # pseudo-fs path - fspath = self.zip_pre+zip_path - if fspath.startswith(self.egg_root+os.sep): - return fspath[len(self.egg_root)+1:].split(os.sep) + fspath = self.zip_pre + zip_path + if fspath.startswith(self.egg_root + os.sep): + return fspath[len(self.egg_root) + 1:].split(os.sep) raise AssertionError( "%s is not a subpath of %s" % (fspath, self.egg_root) ) @@ -1765,7 +1766,7 @@ class ZipProvider(EggProvider): # so proceed. return real_path # Windows, del old file and retry - elif os.name=='nt': + elif os.name == 'nt': unlink(real_path) rename(tmpnam, real_path) return real_path @@ -1785,7 +1786,7 @@ class ZipProvider(EggProvider): if not os.path.isfile(file_path): return False stat = os.stat(file_path) - if stat.st_size!=size or stat.st_mtime!=timestamp: + if stat.st_size != size or stat.st_mtime != timestamp: return False # check that the contents match zip_contents = self.loader.get_data(zip_path) @@ -1835,6 +1836,7 @@ class ZipProvider(EggProvider): def _resource_to_zip(self, resource_name): return self._zipinfo_name(self._fn(self.module_path, resource_name)) + register_loader_type(zipimport.zipimporter, ZipProvider) @@ -1854,20 +1856,24 @@ class FileMetadata(EmptyProvider): self.path = path def has_metadata(self, name): - return name=='PKG-INFO' and os.path.isfile(self.path) + return name == 'PKG-INFO' and os.path.isfile(self.path) def get_metadata(self, name): - if name=='PKG-INFO': - with io.open(self.path, encoding='utf-8') as f: - try: - metadata = f.read() - except UnicodeDecodeError as exc: - # add path context to error message - tmpl = " in {self.path}" - exc.reason += tmpl.format(self=self) - raise - return metadata - raise KeyError("No metadata except PKG-INFO is available") + if name != 'PKG-INFO': + raise KeyError("No metadata except PKG-INFO is available") + + with io.open(self.path, encoding='utf-8', errors="replace") as f: + metadata = f.read() + self._warn_on_replacement(metadata) + return metadata + + def _warn_on_replacement(self, metadata): + # Python 2.6 and 3.2 compat for: replacement_char = '�' + replacement_char = b'\xef\xbf\xbd'.decode('utf-8') + if replacement_char in metadata: + tmpl = "{self.path} could not be properly decoded in UTF-8" + msg = tmpl.format(**locals()) + warnings.warn(msg) def get_metadata_lines(self, name): return yield_lines(self.get_metadata(name)) @@ -1904,7 +1910,7 @@ class EggMetadata(ZipProvider): def __init__(self, importer): """Create a metadata provider from a zipimporter""" - self.zip_pre = importer.archive+os.sep + self.zip_pre = importer.archive + os.sep self.loader = importer if importer.prefix: self.module_path = os.path.join(importer.archive, importer.prefix) @@ -1912,7 +1918,9 @@ class EggMetadata(ZipProvider): self.module_path = importer.archive self._setup_prefix() -_declare_state('dict', _distribution_finders = {}) + +_declare_state('dict', _distribution_finders={}) + def register_finder(importer_type, distribution_finder): """Register `distribution_finder` to find distributions in sys.path items @@ -1930,6 +1938,7 @@ def find_distributions(path_item, only=False): finder = _find_adapter(_distribution_finders, importer) return finder(importer, path_item, only) + def find_eggs_in_zip(importer, path_item, only=False): """ Find eggs in zip files; possibly multiple nested eggs. @@ -1950,12 +1959,17 @@ def find_eggs_in_zip(importer, path_item, only=False): for dist in find_eggs_in_zip(zipimport.zipimporter(subpath), subpath): yield dist + register_finder(zipimport.zipimporter, find_eggs_in_zip) + def find_nothing(importer, path_item, only=False): return () + + register_finder(object, find_nothing) + def find_on_path(importer, path_item, only=False): """Yield distributions accessible on a sys.path directory""" path_item = _normalize_cached(path_item) @@ -1964,7 +1978,7 @@ def find_on_path(importer, path_item, only=False): if _is_unpacked_egg(path_item): yield Distribution.from_filename( path_item, metadata=PathMetadata( - path_item, os.path.join(path_item,'EGG-INFO') + path_item, os.path.join(path_item, 'EGG-INFO') ) ) else: @@ -1996,6 +2010,8 @@ def find_on_path(importer, path_item, only=False): for item in dists: yield item break + + register_finder(pkgutil.ImpImporter, find_on_path) if hasattr(importlib_machinery, 'FileFinder'): @@ -2022,6 +2038,7 @@ def register_namespace_handler(importer_type, namespace_handler): """ _namespace_handlers[importer_type] = namespace_handler + def _handle_ns(packageName, path_item): """Ensure that named package includes a subpath of path_item (if needed)""" @@ -2036,7 +2053,7 @@ def _handle_ns(packageName, path_item): module = sys.modules[packageName] = types.ModuleType(packageName) module.__path__ = [] _set_parent_ns(packageName) - elif not hasattr(module,'__path__'): + elif not hasattr(module, '__path__'): raise TypeError("Not a package:", packageName) handler = _find_adapter(_namespace_handlers, importer) subpath = handler(importer, path_item, packageName, module) @@ -2054,6 +2071,16 @@ def _rebuild_mod_path(orig_path, package_name, module): corresponding to their sys.path order """ sys_path = [_normalize_cached(p) for p in sys.path] + + def safe_sys_path_index(entry): + """ + Workaround for #520 and #513. + """ + try: + return sys_path.index(entry) + except ValueError: + return float('inf') + def position_in_sys_path(path): """ Return the ordinal of the path based on its position in sys.path @@ -2061,7 +2088,7 @@ def _rebuild_mod_path(orig_path, package_name, module): path_parts = path.split(os.sep) module_parts = package_name.count('.') + 1 parts = path_parts[:-module_parts] - return sys_path.index(_normalize_cached(os.sep.join(parts))) + return safe_sys_path_index(_normalize_cached(os.sep.join(parts))) orig_path.sort(key=position_in_sys_path) module.__path__[:] = [_normalize_cached(p) for p in orig_path] @@ -2088,8 +2115,8 @@ def declare_namespace(packageName): # Track what packages are namespaces, so when new path items are added, # they can be updated - _namespace_packages.setdefault(parent,[]).append(packageName) - _namespace_packages.setdefault(packageName,[]) + _namespace_packages.setdefault(parent, []).append(packageName) + _namespace_packages.setdefault(packageName, []) for path_item in path: # Ensure all the parent's path items are reflected in the child, @@ -2099,29 +2126,32 @@ def declare_namespace(packageName): finally: _imp.release_lock() + def fixup_namespace_packages(path_item, parent=None): """Ensure that previously-declared namespace packages include path_item""" _imp.acquire_lock() try: - for package in _namespace_packages.get(parent,()): + for package in _namespace_packages.get(parent, ()): subpath = _handle_ns(package, path_item) if subpath: fixup_namespace_packages(subpath, package) finally: _imp.release_lock() + def file_ns_handler(importer, path_item, packageName, module): """Compute an ns-package subpath for a filesystem or zipfile importer""" subpath = os.path.join(path_item, packageName.split('.')[-1]) normalized = _normalize_cached(subpath) for item in module.__path__: - if _normalize_cached(item)==normalized: + if _normalize_cached(item) == normalized: break else: # Only return the path if it's not already there return subpath + register_namespace_handler(pkgutil.ImpImporter, file_ns_handler) register_namespace_handler(zipimport.zipimporter, file_ns_handler) @@ -2132,6 +2162,7 @@ if hasattr(importlib_machinery, 'FileFinder'): def null_ns_handler(importer, path_item, packageName, module): return None + register_namespace_handler(object, null_ns_handler) @@ -2139,6 +2170,7 @@ def normalize_path(filename): """Normalize a file/dir name for comparison purposes""" return os.path.normcase(os.path.realpath(filename)) + def _normalize_cached(filename, _cache={}): try: return _cache[filename] @@ -2146,6 +2178,7 @@ def _normalize_cached(filename, _cache={}): _cache[filename] = result = normalize_path(filename) return result + def _is_unpacked_egg(path): """ Determine if given path appears to be an unpacked egg. @@ -2154,6 +2187,7 @@ def _is_unpacked_egg(path): path.lower().endswith('.egg') ) + def _set_parent_ns(packageName): parts = packageName.split('.') name = parts.pop() @@ -2175,6 +2209,7 @@ def yield_lines(strs): for s in yield_lines(ss): yield s + MODULE = re.compile(r"\w+(\.\w+)*$").match EGG_NAME = re.compile( r""" @@ -2293,7 +2328,7 @@ class EntryPoint(object): ep = cls.parse(line, dist) if ep.name in this: raise ValueError("Duplicate entry point", group, ep.name) - this[ep.name]=ep + this[ep.name] = ep return this @classmethod @@ -2355,7 +2390,7 @@ class Distribution(object): @classmethod def from_location(cls, location, basename, metadata=None, **kw): - project_name, version, py_version, platform = [None]*4 + project_name, version, py_version, platform = [None] * 4 basename, ext = os.path.splitext(basename) if ext.lower() in _distributionImpl: cls = _distributionImpl[ext.lower()] @@ -2477,11 +2512,11 @@ class Distribution(object): extra, marker = extra.split(':', 1) if invalid_marker(marker): # XXX warn - reqs=[] + reqs = [] elif not evaluate_marker(marker): - reqs=[] + reqs = [] extra = safe_extra(extra) or None - dm.setdefault(extra,[]).extend(parse_requirements(reqs)) + dm.setdefault(extra, []).extend(parse_requirements(reqs)) return dm def requires(self, extras=()): @@ -2503,11 +2538,11 @@ class Distribution(object): for line in self.get_metadata_lines(name): yield line - def activate(self, path=None): + def activate(self, path=None, replace=False): """Ensure distribution is importable on `path` (default=sys.path)""" if path is None: path = sys.path - self.insert_on(path, replace=True) + self.insert_on(path, replace=replace) if path is sys.path: fixup_namespace_packages(self.location) for pkg in self._get_metadata('namespace_packages.txt'): @@ -2577,7 +2612,7 @@ class Distribution(object): self._get_metadata('entry_points.txt'), self ) if group is not None: - return ep_map.get(group,{}) + return ep_map.get(group, {}) return ep_map def get_entry_info(self, group, name): @@ -2585,7 +2620,24 @@ class Distribution(object): return self.get_entry_map(group).get(name) def insert_on(self, path, loc=None, replace=False): - """Insert self.location in path before its nearest parent directory""" + """Ensure self.location is on path + + If replace=False (default): + - If location is already in path anywhere, do nothing. + - Else: + - If it's an egg and its parent directory is on path, + insert just ahead of the parent. + - Else: add to the end of path. + If replace=True: + - If location is already on path anywhere (not eggs) + or higher priority than its parent (eggs) + do nothing. + - Else: + - If it's an egg and its parent directory is on path, + insert just ahead of the parent, + removing any lower-priority entries. + - Else: add it to the front of path. + """ loc = loc or self.location if not loc: @@ -2593,13 +2645,20 @@ class Distribution(object): nloc = _normalize_cached(loc) bdir = os.path.dirname(nloc) - npath= [(p and _normalize_cached(p) or p) for p in path] + npath = [(p and _normalize_cached(p) or p) for p in path] for p, item in enumerate(npath): if item == nloc: - break + if replace: + break + else: + # don't modify path (even removing duplicates) if found and not replace + return elif item == bdir and self.precedence == EGG_DIST: # if it's an .egg, give it precedence over its directory + # UNLESS it's already been added to sys.path and replace=False + if (not replace) and nloc in npath[p:]: + return if path is sys.path: self.check_version_conflict() path.insert(p, loc) @@ -2617,7 +2676,7 @@ class Distribution(object): # p is the spot where we found or inserted loc; now remove duplicates while True: try: - np = npath.index(nloc, p+1) + np = npath.index(nloc, p + 1) except ValueError: break else: @@ -2657,7 +2716,7 @@ class Distribution(object): return False return True - def clone(self,**kw): + def clone(self, **kw): """Copy this distribution, substituting in any changed keyword args""" names = 'project_name version py_version platform location precedence' for attr in names.split(): @@ -2744,7 +2803,7 @@ _distributionImpl = { } -def issue_warning(*args,**kw): +def issue_warning(*args, **kw): level = 1 g = globals() try: @@ -2758,6 +2817,7 @@ def issue_warning(*args,**kw): class RequirementParseError(ValueError): + def __str__(self): return ' '.join(self.args) @@ -2782,6 +2842,7 @@ def parse_requirements(strs): class Requirement(packaging.requirements.Requirement): + def __init__(self, requirement_string): """DO NOT CALL THIS UNDOCUMENTED METHOD; use Requirement.parse()!""" try: @@ -2837,10 +2898,12 @@ class Requirement(packaging.requirements.Requirement): def _get_mro(cls): """Get an mro for a type or classic class""" if not isinstance(cls, type): - class cls(cls, object): pass + class cls(cls, object): + pass return cls.__mro__[1:] return cls.__mro__ + def _find_adapter(registry, ob): """Return an adapter factory for `ob` from `registry`""" for t in _get_mro(getattr(ob, '__class__', type(ob))): @@ -2890,12 +2953,13 @@ def split_sections(s): # wrap up last segment yield section, content -def _mkstemp(*args,**kw): + +def _mkstemp(*args, **kw): old_open = os.open try: # temporarily bypass sandboxing os.open = os_open - return tempfile.mkstemp(*args,**kw) + return tempfile.mkstemp(*args, **kw) finally: # and then put it back os.open = old_open @@ -2946,11 +3010,16 @@ def _initialize_master_working_set(): run_script = working_set.run_script # backward compatibility run_main = run_script - # Activate all distributions already on sys.path, and ensure that - # all distributions added to the working set in the future (e.g. by - # calling ``require()``) will get activated as well. - add_activation_listener(lambda dist: dist.activate()) - working_set.entries=[] + # Activate all distributions already on sys.path with replace=False and + # ensure that all distributions added to the working set in the future + # (e.g. by calling ``require()``) will get activated as well, + # with higher priority (replace=True). + dist = None # ensure dist is defined for del dist below + for dist in working_set: + dist.activate(replace=False) + del dist + add_activation_listener(lambda dist: dist.activate(replace=True), existing=False) + working_set.entries = [] # match order list(map(working_set.add_entry, sys.path)) globals().update(locals()) diff --git a/pkg_resources/_vendor/appdirs.py b/pkg_resources/_vendor/appdirs.py new file mode 100644 index 00000000..f4dba095 --- /dev/null +++ b/pkg_resources/_vendor/appdirs.py @@ -0,0 +1,552 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# Copyright (c) 2005-2010 ActiveState Software Inc. +# Copyright (c) 2013 Eddy Petrișor + +"""Utilities for determining application-specific dirs. + +See <http://github.com/ActiveState/appdirs> for details and usage. +""" +# Dev Notes: +# - MSDN on where to store app data files: +# http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120 +# - Mac OS X: http://developer.apple.com/documentation/MacOSX/Conceptual/BPFileSystem/index.html +# - XDG spec for Un*x: http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html + +__version_info__ = (1, 4, 0) +__version__ = '.'.join(map(str, __version_info__)) + + +import sys +import os + +PY3 = sys.version_info[0] == 3 + +if PY3: + unicode = str + +if sys.platform.startswith('java'): + import platform + os_name = platform.java_ver()[3][0] + if os_name.startswith('Windows'): # "Windows XP", "Windows 7", etc. + system = 'win32' + elif os_name.startswith('Mac'): # "Mac OS X", etc. + system = 'darwin' + else: # "Linux", "SunOS", "FreeBSD", etc. + # Setting this to "linux2" is not ideal, but only Windows or Mac + # are actually checked for and the rest of the module expects + # *sys.platform* style strings. + system = 'linux2' +else: + system = sys.platform + + + +def user_data_dir(appname=None, appauthor=None, version=None, roaming=False): + r"""Return full path to the user-specific data dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "roaming" (boolean, default False) can be set True to use the Windows + roaming appdata directory. That means that for users on a Windows + network setup for roaming profiles, this user data will be + sync'd on login. See + <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> + for a discussion of issues. + + Typical user data directories are: + Mac OS X: ~/Library/Application Support/<AppName> + Unix: ~/.local/share/<AppName> # or in $XDG_DATA_HOME, if defined + Win XP (not roaming): C:\Documents and Settings\<username>\Application Data\<AppAuthor>\<AppName> + Win XP (roaming): C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName> + Win 7 (not roaming): C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName> + Win 7 (roaming): C:\Users\<username>\AppData\Roaming\<AppAuthor>\<AppName> + + For Unix, we follow the XDG spec and support $XDG_DATA_HOME. + That means, by default "~/.local/share/<AppName>". + """ + if system == "win32": + if appauthor is None: + appauthor = appname + const = roaming and "CSIDL_APPDATA" or "CSIDL_LOCAL_APPDATA" + path = os.path.normpath(_get_win_folder(const)) + if appname: + if appauthor is not False: + path = os.path.join(path, appauthor, appname) + else: + path = os.path.join(path, appname) + elif system == 'darwin': + path = os.path.expanduser('~/Library/Application Support/') + if appname: + path = os.path.join(path, appname) + else: + path = os.getenv('XDG_DATA_HOME', os.path.expanduser("~/.local/share")) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def site_data_dir(appname=None, appauthor=None, version=None, multipath=False): + """Return full path to the user-shared data dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "multipath" is an optional parameter only applicable to *nix + which indicates that the entire list of data dirs should be + returned. By default, the first item from XDG_DATA_DIRS is + returned, or '/usr/local/share/<AppName>', + if XDG_DATA_DIRS is not set + + Typical user data directories are: + Mac OS X: /Library/Application Support/<AppName> + Unix: /usr/local/share/<AppName> or /usr/share/<AppName> + Win XP: C:\Documents and Settings\All Users\Application Data\<AppAuthor>\<AppName> + Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.) + Win 7: C:\ProgramData\<AppAuthor>\<AppName> # Hidden, but writeable on Win 7. + + For Unix, this is using the $XDG_DATA_DIRS[0] default. + + WARNING: Do not use this on Windows. See the Vista-Fail note above for why. + """ + if system == "win32": + if appauthor is None: + appauthor = appname + path = os.path.normpath(_get_win_folder("CSIDL_COMMON_APPDATA")) + if appname: + if appauthor is not False: + path = os.path.join(path, appauthor, appname) + else: + path = os.path.join(path, appname) + elif system == 'darwin': + path = os.path.expanduser('/Library/Application Support') + if appname: + path = os.path.join(path, appname) + else: + # XDG default for $XDG_DATA_DIRS + # only first, if multipath is False + path = os.getenv('XDG_DATA_DIRS', + os.pathsep.join(['/usr/local/share', '/usr/share'])) + pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)] + if appname: + if version: + appname = os.path.join(appname, version) + pathlist = [os.sep.join([x, appname]) for x in pathlist] + + if multipath: + path = os.pathsep.join(pathlist) + else: + path = pathlist[0] + return path + + if appname and version: + path = os.path.join(path, version) + return path + + +def user_config_dir(appname=None, appauthor=None, version=None, roaming=False): + r"""Return full path to the user-specific config dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "roaming" (boolean, default False) can be set True to use the Windows + roaming appdata directory. That means that for users on a Windows + network setup for roaming profiles, this user data will be + sync'd on login. See + <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> + for a discussion of issues. + + Typical user data directories are: + Mac OS X: same as user_data_dir + Unix: ~/.config/<AppName> # or in $XDG_CONFIG_HOME, if defined + Win *: same as user_data_dir + + For Unix, we follow the XDG spec and support $XDG_CONFIG_HOME. + That means, by deafult "~/.config/<AppName>". + """ + if system in ["win32", "darwin"]: + path = user_data_dir(appname, appauthor, None, roaming) + else: + path = os.getenv('XDG_CONFIG_HOME', os.path.expanduser("~/.config")) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def site_config_dir(appname=None, appauthor=None, version=None, multipath=False): + """Return full path to the user-shared data dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "multipath" is an optional parameter only applicable to *nix + which indicates that the entire list of config dirs should be + returned. By default, the first item from XDG_CONFIG_DIRS is + returned, or '/etc/xdg/<AppName>', if XDG_CONFIG_DIRS is not set + + Typical user data directories are: + Mac OS X: same as site_data_dir + Unix: /etc/xdg/<AppName> or $XDG_CONFIG_DIRS[i]/<AppName> for each value in + $XDG_CONFIG_DIRS + Win *: same as site_data_dir + Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.) + + For Unix, this is using the $XDG_CONFIG_DIRS[0] default, if multipath=False + + WARNING: Do not use this on Windows. See the Vista-Fail note above for why. + """ + if system in ["win32", "darwin"]: + path = site_data_dir(appname, appauthor) + if appname and version: + path = os.path.join(path, version) + else: + # XDG default for $XDG_CONFIG_DIRS + # only first, if multipath is False + path = os.getenv('XDG_CONFIG_DIRS', '/etc/xdg') + pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)] + if appname: + if version: + appname = os.path.join(appname, version) + pathlist = [os.sep.join([x, appname]) for x in pathlist] + + if multipath: + path = os.pathsep.join(pathlist) + else: + path = pathlist[0] + return path + + +def user_cache_dir(appname=None, appauthor=None, version=None, opinion=True): + r"""Return full path to the user-specific cache dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "opinion" (boolean) can be False to disable the appending of + "Cache" to the base app data dir for Windows. See + discussion below. + + Typical user cache directories are: + Mac OS X: ~/Library/Caches/<AppName> + Unix: ~/.cache/<AppName> (XDG default) + Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Cache + Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Cache + + On Windows the only suggestion in the MSDN docs is that local settings go in + the `CSIDL_LOCAL_APPDATA` directory. This is identical to the non-roaming + app data dir (the default returned by `user_data_dir` above). Apps typically + put cache data somewhere *under* the given dir here. Some examples: + ...\Mozilla\Firefox\Profiles\<ProfileName>\Cache + ...\Acme\SuperApp\Cache\1.0 + OPINION: This function appends "Cache" to the `CSIDL_LOCAL_APPDATA` value. + This can be disabled with the `opinion=False` option. + """ + if system == "win32": + if appauthor is None: + appauthor = appname + path = os.path.normpath(_get_win_folder("CSIDL_LOCAL_APPDATA")) + if appname: + if appauthor is not False: + path = os.path.join(path, appauthor, appname) + else: + path = os.path.join(path, appname) + if opinion: + path = os.path.join(path, "Cache") + elif system == 'darwin': + path = os.path.expanduser('~/Library/Caches') + if appname: + path = os.path.join(path, appname) + else: + path = os.getenv('XDG_CACHE_HOME', os.path.expanduser('~/.cache')) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def user_log_dir(appname=None, appauthor=None, version=None, opinion=True): + r"""Return full path to the user-specific log dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "opinion" (boolean) can be False to disable the appending of + "Logs" to the base app data dir for Windows, and "log" to the + base cache dir for Unix. See discussion below. + + Typical user cache directories are: + Mac OS X: ~/Library/Logs/<AppName> + Unix: ~/.cache/<AppName>/log # or under $XDG_CACHE_HOME if defined + Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Logs + Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Logs + + On Windows the only suggestion in the MSDN docs is that local settings + go in the `CSIDL_LOCAL_APPDATA` directory. (Note: I'm interested in + examples of what some windows apps use for a logs dir.) + + OPINION: This function appends "Logs" to the `CSIDL_LOCAL_APPDATA` + value for Windows and appends "log" to the user cache dir for Unix. + This can be disabled with the `opinion=False` option. + """ + if system == "darwin": + path = os.path.join( + os.path.expanduser('~/Library/Logs'), + appname) + elif system == "win32": + path = user_data_dir(appname, appauthor, version) + version = False + if opinion: + path = os.path.join(path, "Logs") + else: + path = user_cache_dir(appname, appauthor, version) + version = False + if opinion: + path = os.path.join(path, "log") + if appname and version: + path = os.path.join(path, version) + return path + + +class AppDirs(object): + """Convenience wrapper for getting application dirs.""" + def __init__(self, appname, appauthor=None, version=None, roaming=False, + multipath=False): + self.appname = appname + self.appauthor = appauthor + self.version = version + self.roaming = roaming + self.multipath = multipath + + @property + def user_data_dir(self): + return user_data_dir(self.appname, self.appauthor, + version=self.version, roaming=self.roaming) + + @property + def site_data_dir(self): + return site_data_dir(self.appname, self.appauthor, + version=self.version, multipath=self.multipath) + + @property + def user_config_dir(self): + return user_config_dir(self.appname, self.appauthor, + version=self.version, roaming=self.roaming) + + @property + def site_config_dir(self): + return site_config_dir(self.appname, self.appauthor, + version=self.version, multipath=self.multipath) + + @property + def user_cache_dir(self): + return user_cache_dir(self.appname, self.appauthor, + version=self.version) + + @property + def user_log_dir(self): + return user_log_dir(self.appname, self.appauthor, + version=self.version) + + +#---- internal support stuff + +def _get_win_folder_from_registry(csidl_name): + """This is a fallback technique at best. I'm not sure if using the + registry for this guarantees us the correct answer for all CSIDL_* + names. + """ + import _winreg + + shell_folder_name = { + "CSIDL_APPDATA": "AppData", + "CSIDL_COMMON_APPDATA": "Common AppData", + "CSIDL_LOCAL_APPDATA": "Local AppData", + }[csidl_name] + + key = _winreg.OpenKey( + _winreg.HKEY_CURRENT_USER, + r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders" + ) + dir, type = _winreg.QueryValueEx(key, shell_folder_name) + return dir + + +def _get_win_folder_with_pywin32(csidl_name): + from win32com.shell import shellcon, shell + dir = shell.SHGetFolderPath(0, getattr(shellcon, csidl_name), 0, 0) + # Try to make this a unicode path because SHGetFolderPath does + # not return unicode strings when there is unicode data in the + # path. + try: + dir = unicode(dir) + + # Downgrade to short path name if have highbit chars. See + # <http://bugs.activestate.com/show_bug.cgi?id=85099>. + has_high_char = False + for c in dir: + if ord(c) > 255: + has_high_char = True + break + if has_high_char: + try: + import win32api + dir = win32api.GetShortPathName(dir) + except ImportError: + pass + except UnicodeError: + pass + return dir + + +def _get_win_folder_with_ctypes(csidl_name): + import ctypes + + csidl_const = { + "CSIDL_APPDATA": 26, + "CSIDL_COMMON_APPDATA": 35, + "CSIDL_LOCAL_APPDATA": 28, + }[csidl_name] + + buf = ctypes.create_unicode_buffer(1024) + ctypes.windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf) + + # Downgrade to short path name if have highbit chars. See + # <http://bugs.activestate.com/show_bug.cgi?id=85099>. + has_high_char = False + for c in buf: + if ord(c) > 255: + has_high_char = True + break + if has_high_char: + buf2 = ctypes.create_unicode_buffer(1024) + if ctypes.windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024): + buf = buf2 + + return buf.value + +def _get_win_folder_with_jna(csidl_name): + import array + from com.sun import jna + from com.sun.jna.platform import win32 + + buf_size = win32.WinDef.MAX_PATH * 2 + buf = array.zeros('c', buf_size) + shell = win32.Shell32.INSTANCE + shell.SHGetFolderPath(None, getattr(win32.ShlObj, csidl_name), None, win32.ShlObj.SHGFP_TYPE_CURRENT, buf) + dir = jna.Native.toString(buf.tostring()).rstrip("\0") + + # Downgrade to short path name if have highbit chars. See + # <http://bugs.activestate.com/show_bug.cgi?id=85099>. + has_high_char = False + for c in dir: + if ord(c) > 255: + has_high_char = True + break + if has_high_char: + buf = array.zeros('c', buf_size) + kernel = win32.Kernel32.INSTANCE + if kernal.GetShortPathName(dir, buf, buf_size): + dir = jna.Native.toString(buf.tostring()).rstrip("\0") + + return dir + +if system == "win32": + try: + import win32com.shell + _get_win_folder = _get_win_folder_with_pywin32 + except ImportError: + try: + from ctypes import windll + _get_win_folder = _get_win_folder_with_ctypes + except ImportError: + try: + import com.sun.jna + _get_win_folder = _get_win_folder_with_jna + except ImportError: + _get_win_folder = _get_win_folder_from_registry + + +#---- self test code + +if __name__ == "__main__": + appname = "MyApp" + appauthor = "MyCompany" + + props = ("user_data_dir", "site_data_dir", + "user_config_dir", "site_config_dir", + "user_cache_dir", "user_log_dir") + + print("-- app dirs (with optional 'version')") + dirs = AppDirs(appname, appauthor, version="1.0") + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) + + print("\n-- app dirs (without optional 'version')") + dirs = AppDirs(appname, appauthor) + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) + + print("\n-- app dirs (without optional 'appauthor')") + dirs = AppDirs(appname) + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) + + print("\n-- app dirs (with disabled 'appauthor')") + dirs = AppDirs(appname, appauthor=False) + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) diff --git a/pkg_resources/_vendor/pyparsing.py b/pkg_resources/_vendor/pyparsing.py index 3e02dbee..d602a35a 100644..100755 --- a/pkg_resources/_vendor/pyparsing.py +++ b/pkg_resources/_vendor/pyparsing.py @@ -1,6 +1,6 @@ # module pyparsing.py
#
-# Copyright (c) 2003-2015 Paul T. McGuire
+# Copyright (c) 2003-2016 Paul T. McGuire
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
@@ -31,15 +31,18 @@ vs. the traditional lex/yacc approach, or the use of regular expressions. With 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 C{"<salutation>, <addressee>!"})::
+Here is a program to parse "Hello, World!" (or any greeting of the form
+C{"<salutation>, <addressee>!"}), built up using L{Word}, L{Literal}, and L{And} elements
+(L{'+'<ParserElement.__add__>} operator gives L{And} expressions, strings are auto-converted to
+L{Literal} expressions)::
from pyparsing import Word, alphas
# define grammar of a greeting
- greet = Word( alphas ) + "," + Word( alphas ) + "!"
+ greet = Word(alphas) + "," + Word(alphas) + "!"
hello = "Hello, World!"
- print (hello, "->", greet.parseString( hello ))
+ print (hello, "->", greet.parseString(hello))
The program outputs the following::
@@ -48,7 +51,7 @@ The program outputs the following:: 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 C{parseString()} can be accessed as a nested list, a dictionary, or an
+The L{ParseResults} object returned from L{ParserElement.parseString<ParserElement.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:
@@ -57,8 +60,8 @@ The pyparsing module handles some of the problems that are typically vexing when - embedded comments
"""
-__version__ = "2.0.6"
-__versionTime__ = "9 Nov 2015 19:03"
+__version__ = "2.1.9"
+__versionTime__ = "10 Sep 2016 15:10 UTC"
__author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"
import string
@@ -70,8 +73,22 @@ import re import sre_constants
import collections
import pprint
-import functools
-import itertools
+import traceback
+import types
+from datetime import datetime
+
+try:
+ from _thread import RLock
+except ImportError:
+ from threading import RLock
+
+try:
+ from collections import OrderedDict as _OrderedDict
+except ImportError:
+ try:
+ from ordereddict import OrderedDict as _OrderedDict
+ except ImportError:
+ _OrderedDict = None
#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )
@@ -81,21 +98,23 @@ __all__ = [ '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',
+'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter',
'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore',
'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col',
'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString',
'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums',
-'htmlComment', 'javaStyleComment', 'keepOriginalText', 'line', 'lineEnd', 'lineStart', 'lineno',
+'htmlComment', 'javaStyleComment', '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', 'ungroup', 'infixNotation','locatedExpr', 'withClass',
+'CloseMatch', 'tokenMap', 'pyparsing_common',
]
-PY_3 = sys.version.startswith('3')
+system_version = tuple(sys.version_info)[:3]
+PY_3 = system_version[0] == 3
if PY_3:
_MAX_INT = sys.maxsize
basestring = str
@@ -123,18 +142,11 @@ else: 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 encode it
+ ret = unicode(obj).encode(sys.getdefaultencoding(), 'xmlcharrefreplace')
+ xmlcharref = Regex('&#\d+;')
+ xmlcharref.setParseAction(lambda t: '\\u' + hex(int(t[0][2:-1]))[2:])
+ return xmlcharref.transformString(ret)
# build list of single arg builtins, tolerant of Python version, that can be used as parse actions
singleArgBuiltins = []
@@ -160,7 +172,7 @@ def _xml_escape(data): class _Constants(object):
pass
-alphas = string.ascii_lowercase + string.ascii_uppercase
+alphas = string.ascii_uppercase + string.ascii_lowercase
nums = "0123456789"
hexnums = nums + "ABCDEFabcdef"
alphanums = alphas + nums
@@ -180,6 +192,15 @@ class ParseBaseException(Exception): self.msg = msg
self.pstr = pstr
self.parserElement = elem
+ self.args = (pstr, loc, msg)
+
+ @classmethod
+ def _from_exception(cls, pe):
+ """
+ internal factory method to simplify creating one type of ParseException
+ from another - avoids having __init__ signature conflicts among subclasses
+ """
+ return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement)
def __getattr__( self, aname ):
"""supported attributes by name are:
@@ -212,15 +233,26 @@ class ParseBaseException(Exception): markerString, line_str[line_column:]))
return line_str.strip()
def __dir__(self):
- return "loc msg pstr parserElement lineno col line " \
- "markInputline __str__ __repr__".split()
+ return "lineno col line".split() + dir(type(self))
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
+ """
+ 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
+
+ Example::
+ try:
+ Word(nums).setName("integer").parseString("ABC")
+ except ParseException as pe:
+ print(pe)
+ print("column: {}".format(pe.col))
+
+ prints::
+ Expected integer (at char 0), (line:1, col:1)
+ column: 1
"""
pass
@@ -230,12 +262,10 @@ class ParseFatalException(ParseBaseException): pass
class ParseSyntaxException(ParseFatalException):
- """just like C{L{ParseFatalException}}, but thrown internally when an
- C{L{ErrorStop<And._ErrorStop>}} ('-' operator) 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)
+ """just like L{ParseFatalException}, but thrown internally when an
+ L{ErrorStop<And._ErrorStop>} ('-' operator) indicates that parsing is to stop
+ immediately because an unbacktrackable syntax error has been found"""
+ pass
#~ class ReparseException(ParseBaseException):
#~ """Experimental class - parse actions can raise this exception to cause
@@ -251,7 +281,7 @@ class ParseSyntaxException(ParseFatalException): #~ self.reparseLoc = restartLoc
class RecursiveGrammarException(Exception):
- """exception thrown by C{validate()} if the grammar could be improperly recursive"""
+ """exception thrown by L{ParserElement.validate} if the grammar could be improperly recursive"""
def __init__( self, parseElementList ):
self.parseElementTrace = parseElementList
@@ -264,17 +294,50 @@ class _ParseResultsWithOffset(object): def __getitem__(self,i):
return self.tup[i]
def __repr__(self):
- return repr(self.tup)
+ return repr(self.tup[0])
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:
+ """
+ Structured parse results, to provide multiple means of access to the parsed data:
- as a list (C{len(results)})
- by list index (C{results[0], results[1]}, etc.)
- - by attribute (C{results.<resultsName>})
- """
- def __new__(cls, toklist, name=None, asList=True, modal=True ):
+ - by attribute (C{results.<resultsName>} - see L{ParserElement.setResultsName})
+
+ Example::
+ integer = Word(nums)
+ date_str = (integer.setResultsName("year") + '/'
+ + integer.setResultsName("month") + '/'
+ + integer.setResultsName("day"))
+ # equivalent form:
+ # date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ # parseString returns a ParseResults object
+ result = date_str.parseString("1999/12/31")
+
+ def test(s, fn=repr):
+ print("%s -> %s" % (s, fn(eval(s))))
+ test("list(result)")
+ test("result[0]")
+ test("result['month']")
+ test("result.day")
+ test("'month' in result")
+ test("'minutes' in result")
+ test("result.dump()", str)
+ prints::
+ list(result) -> ['1999', '/', '12', '/', '31']
+ result[0] -> '1999'
+ result['month'] -> '12'
+ result.day -> '31'
+ 'month' in result -> True
+ 'minutes' in result -> False
+ result.dump() -> ['1999', '/', '12', '/', '31']
+ - day: 31
+ - month: 12
+ - year: 1999
+ """
+ def __new__(cls, toklist=None, name=None, asList=True, modal=True ):
if isinstance(toklist, cls):
return toklist
retobj = object.__new__(cls)
@@ -283,12 +346,16 @@ class ParseResults(object): # 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, isinstance=isinstance ):
+ def __init__( self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance ):
if self.__doinit:
self.__doinit = False
self.__name = None
self.__parent = None
self.__accumNames = {}
+ self.__asList = asList
+ self.__modal = modal
+ if toklist is None:
+ toklist = []
if isinstance(toklist, list):
self.__toklist = toklist[:]
elif isinstance(toklist, _generatorType):
@@ -331,7 +398,7 @@ class ParseResults(object): if isinstance(v,_ParseResultsWithOffset):
self.__tokdict[k] = self.__tokdict.get(k,list()) + [v]
sub = v[0]
- elif isinstance(k,int):
+ elif isinstance(k,(int,slice)):
self.__toklist[k] = v
sub = v
else:
@@ -354,11 +421,6 @@ class ParseResults(object): 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))
for name,occurrences in self.__tokdict.items():
for j in removed:
for k, (value, position) in enumerate(occurrences):
@@ -370,39 +432,52 @@ class ParseResults(object): return k in self.__tokdict
def __len__( self ): return len( self.__toklist )
- def __bool__(self): return len( self.__toklist ) > 0
+ def __bool__(self): return ( not not self.__toklist )
__nonzero__ = __bool__
def __iter__( self ): return iter( self.__toklist )
def __reversed__( self ): return iter( self.__toklist[::-1] )
- def iterkeys( self ):
- """Returns all named result keys."""
+ def _iterkeys( self ):
if hasattr(self.__tokdict, "iterkeys"):
return self.__tokdict.iterkeys()
else:
return iter(self.__tokdict)
- def itervalues( self ):
- """Returns all named result values."""
- return (self[k] for k in self.iterkeys())
+ def _itervalues( self ):
+ return (self[k] for k in self._iterkeys())
- def iteritems( self ):
- return ((k, self[k]) for k in self.iterkeys())
+ def _iteritems( self ):
+ return ((k, self[k]) for k in self._iterkeys())
if PY_3:
- keys = iterkeys
- values = itervalues
- items = iteritems
+ keys = _iterkeys
+ """Returns an iterator of all named result keys (Python 3.x only)."""
+
+ values = _itervalues
+ """Returns an iterator of all named result values (Python 3.x only)."""
+
+ items = _iteritems
+ """Returns an iterator of all named result key-value tuples (Python 3.x only)."""
+
else:
+ iterkeys = _iterkeys
+ """Returns an iterator of all named result keys (Python 2.x only)."""
+
+ itervalues = _itervalues
+ """Returns an iterator of all named result values (Python 2.x only)."""
+
+ iteritems = _iteritems
+ """Returns an iterator of all named result key-value tuples (Python 2.x only)."""
+
def keys( self ):
- """Returns all named result keys."""
+ """Returns all named result keys (as a list in Python 2.x, as an iterator in Python 3.x)."""
return list(self.iterkeys())
def values( self ):
- """Returns all named result values."""
+ """Returns all named result values (as a list in Python 2.x, as an iterator in Python 3.x)."""
return list(self.itervalues())
def items( self ):
- """Returns all named result keys and values as a list of tuples."""
+ """Returns all named result key-values (as a list of tuples in Python 2.x, as an iterator in Python 3.x)."""
return list(self.iteritems())
def haskeys( self ):
@@ -411,14 +486,39 @@ class ParseResults(object): return bool(self.__tokdict)
def pop( self, *args, **kwargs):
- """Removes and returns item at specified index (default=last).
- Supports both list and dict semantics for pop(). If passed no
- argument or an integer argument, it will use list semantics
- and pop tokens from the list of parsed tokens. If passed a
- non-integer argument (most likely a string), it will use dict
- semantics and pop the corresponding value from any defined
- results names. A second default return value argument is
- supported, just as in dict.pop()."""
+ """
+ Removes and returns item at specified index (default=C{last}).
+ Supports both C{list} and C{dict} semantics for C{pop()}. If passed no
+ argument or an integer argument, it will use C{list} semantics
+ and pop tokens from the list of parsed tokens. If passed a
+ non-integer argument (most likely a string), it will use C{dict}
+ semantics and pop the corresponding value from any defined
+ results names. A second default return value argument is
+ supported, just as in C{dict.pop()}.
+
+ Example::
+ def remove_first(tokens):
+ tokens.pop(0)
+ print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
+ print(OneOrMore(Word(nums)).addParseAction(remove_first).parseString("0 123 321")) # -> ['123', '321']
+
+ label = Word(alphas)
+ patt = label("LABEL") + OneOrMore(Word(nums))
+ print(patt.parseString("AAB 123 321").dump())
+
+ # Use pop() in a parse action to remove named result (note that corresponding value is not
+ # removed from list form of results)
+ def remove_LABEL(tokens):
+ tokens.pop("LABEL")
+ return tokens
+ patt.addParseAction(remove_LABEL)
+ print(patt.parseString("AAB 123 321").dump())
+ prints::
+ ['AAB', '123', '321']
+ - LABEL: AAB
+
+ ['AAB', '123', '321']
+ """
if not args:
args = [-1]
for k,v in kwargs.items():
@@ -438,39 +538,83 @@ class ParseResults(object): return defaultvalue
def get(self, key, defaultValue=None):
- """Returns named result matching the given key, or if there is no
- such name, then returns the given C{defaultValue} or C{None} if no
- C{defaultValue} is specified."""
+ """
+ Returns named result matching the given key, or if there is no
+ such name, then returns the given C{defaultValue} or C{None} if no
+ C{defaultValue} is specified.
+
+ Similar to C{dict.get()}.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ result = date_str.parseString("1999/12/31")
+ print(result.get("year")) # -> '1999'
+ print(result.get("hour", "not specified")) # -> 'not specified'
+ print(result.get("hour")) # -> None
+ """
if key in self:
return self[key]
else:
return defaultValue
def insert( self, index, insStr ):
- """Inserts new element at location index in the list of parsed tokens."""
+ """
+ Inserts new element at location index in the list of parsed tokens.
+
+ Similar to C{list.insert()}.
+
+ Example::
+ print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
+
+ # use a parse action to insert the parse location in the front of the parsed results
+ def insert_locn(locn, tokens):
+ tokens.insert(0, locn)
+ print(OneOrMore(Word(nums)).addParseAction(insert_locn).parseString("0 123 321")) # -> [0, '0', '123', '321']
+ """
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))
for name,occurrences in self.__tokdict.items():
for k, (value, position) in enumerate(occurrences):
occurrences[k] = _ParseResultsWithOffset(value, position + (position > index))
def append( self, item ):
- """Add single element to end of ParseResults list of elements."""
+ """
+ Add single element to end of ParseResults list of elements.
+
+ Example::
+ print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
+
+ # use a parse action to compute the sum of the parsed integers, and add it to the end
+ def append_sum(tokens):
+ tokens.append(sum(map(int, tokens)))
+ print(OneOrMore(Word(nums)).addParseAction(append_sum).parseString("0 123 321")) # -> ['0', '123', '321', 444]
+ """
self.__toklist.append(item)
def extend( self, itemseq ):
- """Add sequence of elements to end of ParseResults list of elements."""
+ """
+ Add sequence of elements to end of ParseResults list of elements.
+
+ Example::
+ patt = OneOrMore(Word(alphas))
+
+ # use a parse action to append the reverse of the matched strings, to make a palindrome
+ def make_palindrome(tokens):
+ tokens.extend(reversed([t[::-1] for t in tokens]))
+ return ''.join(tokens)
+ print(patt.addParseAction(make_palindrome).parseString("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl'
+ """
if isinstance(itemseq, ParseResults):
self += itemseq
else:
self.__toklist.extend(itemseq)
def clear( self ):
- """Clear all elements and results names."""
+ """
+ Clear all elements and results names.
+ """
del self.__toklist[:]
self.__tokdict.clear()
@@ -511,7 +655,11 @@ class ParseResults(object): def __radd__(self, other):
if isinstance(other,int) and other == 0:
+ # useful for merging many ParseResults using sum() builtin
return self.copy()
+ else:
+ # this may raise a TypeError - so be it
+ return other + self
def __repr__( self ):
return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) )
@@ -531,18 +679,60 @@ class ParseResults(object): return out
def asList( self ):
- """Returns the parse results as a nested list of matching tokens, all converted to strings."""
+ """
+ Returns the parse results as a nested list of matching tokens, all converted to strings.
+
+ Example::
+ patt = OneOrMore(Word(alphas))
+ result = patt.parseString("sldkj lsdkj sldkj")
+ # even though the result prints in string-like form, it is actually a pyparsing ParseResults
+ print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj']
+
+ # Use asList() to create an actual list
+ result_list = result.asList()
+ print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj']
+ """
return [res.asList() if isinstance(res,ParseResults) else res for res in self.__toklist]
def asDict( self ):
- """Returns the named parse results as dictionary."""
+ """
+ Returns the named parse results as a nested dictionary.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ result = date_str.parseString('12/31/1999')
+ print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]})
+
+ result_dict = result.asDict()
+ print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'}
+
+ # even though a ParseResults supports dict-like access, sometime you just need to have a dict
+ import json
+ print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable
+ print(json.dumps(result.asDict())) # -> {"month": "31", "day": "1999", "year": "12"}
+ """
if PY_3:
- return dict( self.items() )
+ item_fn = self.items
else:
- return dict( self.iteritems() )
+ item_fn = self.iteritems
+
+ def toItem(obj):
+ if isinstance(obj, ParseResults):
+ if obj.haskeys():
+ return obj.asDict()
+ else:
+ return [toItem(v) for v in obj]
+ else:
+ return obj
+
+ return dict((k,toItem(v)) for k,v in item_fn())
def copy( self ):
- """Returns a new copy of a C{ParseResults} object."""
+ """
+ Returns a new copy of a C{ParseResults} object.
+ """
ret = ParseResults( self.__toklist )
ret.__tokdict = self.__tokdict.copy()
ret.__parent = self.__parent
@@ -551,7 +741,9 @@ class ParseResults(object): 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."""
+ """
+ (Deprecated) 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()
@@ -617,7 +809,27 @@ class ParseResults(object): return None
def getName(self):
- """Returns the results name for this token expression."""
+ """
+ Returns the results name for this token expression. Useful when several
+ different expressions might match at a particular location.
+
+ Example::
+ integer = Word(nums)
+ ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d")
+ house_number_expr = Suppress('#') + Word(nums, alphanums)
+ user_data = (Group(house_number_expr)("house_number")
+ | Group(ssn_expr)("ssn")
+ | Group(integer)("age"))
+ user_info = OneOrMore(user_data)
+
+ result = user_info.parseString("22 111-22-3333 #221B")
+ for item in result:
+ print(item.getName(), ':', item[0])
+ prints::
+ age : 22
+ ssn : 111-22-3333
+ house_number : 221B
+ """
if self.__name:
return self.__name
elif self.__parent:
@@ -628,45 +840,77 @@ class ParseResults(object): 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]
+ next(iter(self.__tokdict.values()))[0][1] in (0,-1)):
+ return next(iter(self.__tokdict.keys()))
else:
return None
- def dump(self,indent='',depth=0):
- """Diagnostic method for listing out the contents of a C{ParseResults}.
- Accepts an optional C{indent} argument so that this string can be embedded
- in a nested display of other data."""
+ def dump(self, indent='', depth=0, full=True):
+ """
+ Diagnostic method for listing out the contents of a C{ParseResults}.
+ Accepts an optional C{indent} argument so that this string can be embedded
+ in a nested display of other data.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ result = date_str.parseString('12/31/1999')
+ print(result.dump())
+ prints::
+ ['12', '/', '31', '/', '1999']
+ - day: 1999
+ - month: 31
+ - year: 12
+ """
out = []
NL = '\n'
out.append( indent+_ustr(self.asList()) )
- if self.haskeys():
- items = sorted(self.items())
- for k,v in items:
- if out:
- out.append(NL)
- out.append( "%s%s- %s: " % (indent,(' '*depth), k) )
- if isinstance(v,ParseResults):
- if v:
- out.append( v.dump(indent,depth+1) )
+ if full:
+ if self.haskeys():
+ items = sorted(self.items())
+ for k,v in items:
+ if out:
+ out.append(NL)
+ out.append( "%s%s- %s: " % (indent,(' '*depth), k) )
+ if isinstance(v,ParseResults):
+ if v:
+ out.append( v.dump(indent,depth+1) )
+ else:
+ out.append(_ustr(v))
else:
out.append(_ustr(v))
- else:
- out.append(_ustr(v))
- elif any(isinstance(vv,ParseResults) for vv in self):
- v = self
- for i,vv in enumerate(v):
- if isinstance(vv,ParseResults):
- out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),vv.dump(indent,depth+1) ))
- else:
- out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),_ustr(vv)))
+ elif any(isinstance(vv,ParseResults) for vv in self):
+ v = self
+ for i,vv in enumerate(v):
+ if isinstance(vv,ParseResults):
+ out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),vv.dump(indent,depth+1) ))
+ else:
+ out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),_ustr(vv)))
return "".join(out)
def pprint(self, *args, **kwargs):
- """Pretty-printer for parsed results as a list, using the C{pprint} module.
- Accepts additional positional or keyword args as defined for the
- C{pprint.pprint} method. (U{http://docs.python.org/3/library/pprint.html#pprint.pprint})"""
+ """
+ Pretty-printer for parsed results as a list, using the C{pprint} module.
+ Accepts additional positional or keyword args as defined for the
+ C{pprint.pprint} method. (U{http://docs.python.org/3/library/pprint.html#pprint.pprint})
+
+ Example::
+ ident = Word(alphas, alphanums)
+ num = Word(nums)
+ func = Forward()
+ term = ident | num | Group('(' + func + ')')
+ func <<= ident + Group(Optional(delimitedList(term)))
+ result = func.parseString("fna a,b,(fnb c,d,200),100")
+ result.pprint(width=40)
+ prints::
+ ['fna',
+ ['a',
+ 'b',
+ ['(', 'fnb', ['c', 'd', '200'], ')'],
+ '100']]
+ """
pprint.pprint(self.asList(), *args, **kwargs)
# add support for pickle protocol
@@ -690,8 +934,11 @@ class ParseResults(object): else:
self.__parent = None
+ def __getnewargs__(self):
+ return self.__toklist, self.__name, self.__asList, self.__modal
+
def __dir__(self):
- return dir(super(ParseResults,self)) + list(self.keys())
+ return (dir(type(self)) + list(self.keys()))
collections.MutableMapping.register(ParseResults)
@@ -771,6 +1018,31 @@ def _trim_arity(func, maxargs=2): return lambda s,l,t: func(t)
limit = [0]
foundArity = [False]
+
+ # traceback return data structure changed in Py3.5 - normalize back to plain tuples
+ if system_version[:2] >= (3,5):
+ def extract_stack(limit=0):
+ # special handling for Python 3.5.0 - extra deep call stack by 1
+ offset = -3 if system_version == (3,5,0) else -2
+ frame_summary = traceback.extract_stack(limit=-offset+limit-1)[offset]
+ return [(frame_summary.filename, frame_summary.lineno)]
+ def extract_tb(tb, limit=0):
+ frames = traceback.extract_tb(tb, limit=limit)
+ frame_summary = frames[-1]
+ return [(frame_summary.filename, frame_summary.lineno)]
+ else:
+ extract_stack = traceback.extract_stack
+ extract_tb = traceback.extract_tb
+
+ # synthesize what would be returned by traceback.extract_stack at the call to
+ # user's parse action 'func', so that we don't incur call penalty at parse time
+
+ LINE_DIFF = 6
+ # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND
+ # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!!
+ this_line = extract_stack(limit=2)[-1]
+ pa_call_line_synth = (this_line[0], this_line[1]+LINE_DIFF)
+
def wrapper(*args):
while 1:
try:
@@ -778,12 +1050,33 @@ def _trim_arity(func, maxargs=2): foundArity[0] = True
return ret
except TypeError:
- if limit[0] <= maxargs and not foundArity[0]:
+ # re-raise TypeErrors if they did not come from our arity testing
+ if foundArity[0]:
+ raise
+ else:
+ try:
+ tb = sys.exc_info()[-1]
+ if not extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth:
+ raise
+ finally:
+ del tb
+
+ if limit[0] <= maxargs:
limit[0] += 1
continue
raise
+
+ # copy func name to wrapper for sensible debug output
+ func_name = "<parse action>"
+ try:
+ func_name = getattr(func, '__name__',
+ getattr(func, '__class__').__name__)
+ except Exception:
+ func_name = str(func)
+ wrapper.__name__ = func_name
+
return wrapper
-
+
class ParserElement(object):
"""Abstract base level parser element class."""
DEFAULT_WHITE_CHARS = " \n\t\r"
@@ -791,7 +1084,16 @@ class ParserElement(object): @staticmethod
def setDefaultWhitespaceChars( chars ):
- """Overrides the default whitespace chars
+ r"""
+ Overrides the default whitespace chars
+
+ Example::
+ # default whitespace chars are space, <TAB> and newline
+ OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl']
+
+ # change to just treat newline as significant
+ ParserElement.setDefaultWhitespaceChars(" \t")
+ OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def']
"""
ParserElement.DEFAULT_WHITE_CHARS = chars
@@ -799,8 +1101,22 @@ class ParserElement(object): def inlineLiteralsUsing(cls):
"""
Set class to be used for inclusion of string literals into a parser.
+
+ Example::
+ # default literal class used is Literal
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
+
+
+ # change to Suppress
+ ParserElement.inlineLiteralsUsing(Suppress)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ date_str.parseString("1999/12/31") # -> ['1999', '12', '31']
"""
- ParserElement.literalStringClass = cls
+ ParserElement._literalStringClass = cls
def __init__( self, savelist=False ):
self.parseAction = list()
@@ -826,8 +1142,21 @@ class ParserElement(object): self.callDuringTry = False
def copy( self ):
- """Make a copy of this C{ParserElement}. Useful for defining different parse actions
- for the same parsing pattern, using copies of the original parse element."""
+ """
+ Make a copy of this C{ParserElement}. Useful for defining different parse actions
+ for the same parsing pattern, using copies of the original parse element.
+
+ Example::
+ integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ integerK = integer.copy().addParseAction(lambda toks: toks[0]*1024) + Suppress("K")
+ integerM = integer.copy().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
+
+ print(OneOrMore(integerK | integerM | integer).parseString("5K 100 640K 256M"))
+ prints::
+ [5120, 100, 655360, 268435456]
+ Equivalent form of C{expr.copy()} is just C{expr()}::
+ integerM = integer().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
+ """
cpy = copy.copy( self )
cpy.parseAction = self.parseAction[:]
cpy.ignoreExprs = self.ignoreExprs[:]
@@ -836,7 +1165,13 @@ class ParserElement(object): return cpy
def setName( self, name ):
- """Define name for this expression, for use in debugging."""
+ """
+ Define name for this expression, makes debugging and exception messages clearer.
+
+ Example::
+ Word(nums).parseString("ABC") # -> Exception: Expected W:(0123...) (at char 0), (line:1, col:1)
+ Word(nums).setName("integer").parseString("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1)
+ """
self.name = name
self.errmsg = "Expected " + self.name
if hasattr(self,"exception"):
@@ -844,15 +1179,24 @@ class ParserElement(object): 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 C{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.
-
- You can also set results names using the abbreviated syntax,
- C{expr("name")} in place of C{expr.setResultsName("name")} -
- see L{I{__call__}<__call__>}.
+ """
+ Define name for referencing matching tokens as a nested attribute
+ of the returned parse results.
+ NOTE: this returns a *copy* of the original C{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.
+
+ You can also set results names using the abbreviated syntax,
+ C{expr("name")} in place of C{expr.setResultsName("name")} -
+ see L{I{__call__}<__call__>}.
+
+ Example::
+ date_str = (integer.setResultsName("year") + '/'
+ + integer.setResultsName("month") + '/'
+ + integer.setResultsName("day"))
+
+ # equivalent form:
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
"""
newself = self.copy()
if name.endswith("*"):
@@ -881,42 +1225,76 @@ class ParserElement(object): return self
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 C{fn(s,loc,toks)},
- C{fn(loc,toks)}, C{fn(toks)}, or just C{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 C{L{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}<parseString>} for more information
- on parsing strings containing C{<TAB>}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.
- """
+ """
+ Define action to perform when successfully matching parse element definition.
+ Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)},
+ C{fn(loc,toks)}, C{fn(toks)}, or just C{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 C{L{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.
+
+ Optional keyword arguments:
+ - callDuringTry = (default=C{False}) indicate if parse action should be run during lookaheads and alternate testing
+
+ Note: the default parsing behavior is to expand tabs in the input string
+ before starting the parsing process. See L{I{parseString}<parseString>} for more information
+ on parsing strings containing C{<TAB>}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.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer + '/' + integer + '/' + integer
+
+ date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
+
+ # use parse action to convert to ints at parse time
+ integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ date_str = integer + '/' + integer + '/' + integer
+
+ # note that integer fields are now ints, not strings
+ date_str.parseString("1999/12/31") # -> [1999, '/', 12, '/', 31]
+ """
self.parseAction = list(map(_trim_arity, list(fns)))
self.callDuringTry = kwargs.get("callDuringTry", False)
return self
def addParseAction( self, *fns, **kwargs ):
- """Add parse action to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}."""
+ """
+ Add parse action to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}.
+
+ See examples in L{I{copy}<copy>}.
+ """
self.parseAction += list(map(_trim_arity, list(fns)))
self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
return self
def addCondition(self, *fns, **kwargs):
"""Add a boolean predicate function to expression's list of parse actions. See
- L{I{setParseAction}<setParseAction>}. Optional keyword argument C{message} can
- be used to define a custom message to be used in the raised exception."""
- msg = kwargs.get("message") or "failed user-defined condition"
+ L{I{setParseAction}<setParseAction>} for function call signatures. Unlike C{setParseAction},
+ functions passed to C{addCondition} need to return boolean success/fail of the condition.
+
+ Optional keyword arguments:
+ - message = define a custom message to be used in the raised exception
+ - fatal = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise ParseException
+
+ Example::
+ integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ year_int = integer.copy()
+ year_int.addCondition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later")
+ date_str = year_int + '/' + integer + '/' + integer
+
+ result = date_str.parseString("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), (line:1, col:1)
+ """
+ msg = kwargs.get("message", "failed user-defined condition")
+ exc_type = ParseFatalException if kwargs.get("fatal", False) else ParseException
for fn in fns:
def pa(s,l,t):
if not bool(_trim_arity(fn)(s,l,t)):
- raise ParseException(s,l,msg)
- return t
+ raise exc_type(s,l,msg)
self.parseAction.append(pa)
self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
return self
@@ -1043,43 +1421,132 @@ class ParserElement(object): return self._parse( instring, loc, doActions=False )[0]
except ParseFatalException:
raise ParseException( instring, loc, self.errmsg, self)
+
+ def canParseNext(self, instring, loc):
+ try:
+ self.tryParse(instring, loc)
+ except (ParseException, IndexError):
+ return False
+ else:
+ return True
+
+ class _UnboundedCache(object):
+ def __init__(self):
+ cache = {}
+ self.not_in_cache = not_in_cache = object()
+
+ def get(self, key):
+ return cache.get(key, not_in_cache)
+
+ def set(self, key, value):
+ cache[key] = value
+
+ def clear(self):
+ cache.clear()
+
+ self.get = types.MethodType(get, self)
+ self.set = types.MethodType(set, self)
+ self.clear = types.MethodType(clear, self)
+
+ if _OrderedDict is not None:
+ class _FifoCache(object):
+ def __init__(self, size):
+ self.not_in_cache = not_in_cache = object()
+
+ cache = _OrderedDict()
+
+ def get(self, key):
+ return cache.get(key, not_in_cache)
+
+ def set(self, key, value):
+ cache[key] = value
+ if len(cache) > size:
+ cache.popitem(False)
+
+ def clear(self):
+ cache.clear()
+
+ self.get = types.MethodType(get, self)
+ self.set = types.MethodType(set, self)
+ self.clear = types.MethodType(clear, self)
+
+ else:
+ class _FifoCache(object):
+ def __init__(self, size):
+ self.not_in_cache = not_in_cache = object()
+
+ cache = {}
+ key_fifo = collections.deque([], size)
+
+ def get(self, key):
+ return cache.get(key, not_in_cache)
+
+ def set(self, key, value):
+ cache[key] = value
+ if len(cache) > size:
+ cache.pop(key_fifo.popleft(), None)
+ key_fifo.append(key)
+
+ def clear(self):
+ cache.clear()
+ key_fifo.clear()
+
+ self.get = types.MethodType(get, self)
+ self.set = types.MethodType(set, self)
+ self.clear = types.MethodType(clear, self)
+
+ # argument cache for optimizing repeated calls when backtracking through recursive expressions
+ packrat_cache = {} # this is set later by enabledPackrat(); this is here so that resetCache() doesn't fail
+ packrat_cache_lock = RLock()
+ packrat_cache_stats = [0, 0]
# 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[0],value[1].copy())
- else:
- try:
- value = self._parseNoCache( instring, loc, doActions, callPreParse )
- ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy())
- return value
- except ParseBaseException as pe:
- pe.__traceback__ = None
- ParserElement._exprArgCache[ lookup ] = pe
- raise
+ HIT, MISS = 0, 1
+ lookup = (self, instring, loc, callPreParse, doActions)
+ with ParserElement.packrat_cache_lock:
+ cache = ParserElement.packrat_cache
+ value = cache.get(lookup)
+ if value is cache.not_in_cache:
+ ParserElement.packrat_cache_stats[MISS] += 1
+ try:
+ value = self._parseNoCache(instring, loc, doActions, callPreParse)
+ except ParseBaseException as pe:
+ # cache a copy of the exception, without the traceback
+ cache.set(lookup, pe.__class__(*pe.args))
+ raise
+ else:
+ cache.set(lookup, (value[0], value[1].copy()))
+ return value
+ else:
+ ParserElement.packrat_cache_stats[HIT] += 1
+ if isinstance(value, Exception):
+ raise value
+ return (value[0], value[1].copy())
_parse = _parseNoCache
- # argument cache for optimizing repeated calls when backtracking through recursive expressions
- _exprArgCache = {}
@staticmethod
def resetCache():
- ParserElement._exprArgCache.clear()
+ ParserElement.packrat_cache.clear()
+ ParserElement.packrat_cache_stats[:] = [0] * len(ParserElement.packrat_cache_stats)
_packratEnabled = False
@staticmethod
- def enablePackrat():
+ def enablePackrat(cache_size_limit=128):
"""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.
-
+
+ Parameters:
+ - cache_size_limit - (default=C{128}) - if an integer value is provided
+ will limit the size of the packrat cache; if None is passed, then
+ the cache size will be unbounded; if 0 is passed, the cache will
+ be effectively disabled.
+
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
@@ -1088,32 +1555,45 @@ class ParserElement(object): C{enablePackrat} before calling C{psyco.full()}. If you do not do this,
Python will crash. For best results, call C{enablePackrat()} immediately
after importing pyparsing.
+
+ Example::
+ import pyparsing
+ pyparsing.ParserElement.enablePackrat()
"""
if not ParserElement._packratEnabled:
ParserElement._packratEnabled = True
+ if cache_size_limit is None:
+ ParserElement.packrat_cache = ParserElement._UnboundedCache()
+ else:
+ ParserElement.packrat_cache = ParserElement._FifoCache(cache_size_limit)
ParserElement._parse = ParserElement._parseCache
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 C{parseAll} to True (equivalent to ending
- the grammar with C{L{StringEnd()}}).
-
- Note: C{parseString} implicitly calls C{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 C{loc} argument to index into the
- string being parsed, you can ensure you have a consistent view of the input
- string by:
- - calling C{parseWithTabs} on your grammar before calling C{parseString}
- (see L{I{parseWithTabs}<parseWithTabs>})
- - define your parse action using the full C{(s,loc,toks)} signature, and
- reference the input string using the parse action's C{s} argument
- - explictly expand the tabs in your input string before calling
- C{parseString}
+ """
+ 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 C{parseAll} to True (equivalent to ending
+ the grammar with C{L{StringEnd()}}).
+
+ Note: C{parseString} implicitly calls C{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 C{loc} argument to index into the
+ string being parsed, you can ensure you have a consistent view of the input
+ string by:
+ - calling C{parseWithTabs} on your grammar before calling C{parseString}
+ (see L{I{parseWithTabs}<parseWithTabs>})
+ - define your parse action using the full C{(s,loc,toks)} signature, and
+ reference the input string using the parse action's C{s} argument
+ - explictly expand the tabs in your input string before calling
+ C{parseString}
+
+ Example::
+ Word('a').parseString('aaaaabaaa') # -> ['aaaaa']
+ Word('a').parseString('aaaaabaaa', parseAll=True) # -> Exception: Expected end of text
"""
ParserElement.resetCache()
if not self.streamlined:
@@ -1139,14 +1619,35 @@ class ParserElement(object): return tokens
def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ):
- """Scan the input string for expression matches. Each match will return the
- matching tokens, start location, and end location. May be called with optional
- C{maxMatches} argument, to clip scanning after 'n' matches are found. If
- C{overlap} is specified, then overlapping matches will be reported.
-
- Note that the start and end locations are reported relative to the string
- being parsed. See L{I{parseString}<parseString>} for more information on parsing
- strings with embedded tabs."""
+ """
+ Scan the input string for expression matches. Each match will return the
+ matching tokens, start location, and end location. May be called with optional
+ C{maxMatches} argument, to clip scanning after 'n' matches are found. If
+ C{overlap} is specified, then overlapping matches will be reported.
+
+ Note that the start and end locations are reported relative to the string
+ being parsed. See L{I{parseString}<parseString>} for more information on parsing
+ strings with embedded tabs.
+
+ Example::
+ source = "sldjf123lsdjjkf345sldkjf879lkjsfd987"
+ print(source)
+ for tokens,start,end in Word(alphas).scanString(source):
+ print(' '*start + '^'*(end-start))
+ print(' '*start + tokens[0])
+
+ prints::
+
+ sldjf123lsdjjkf345sldkjf879lkjsfd987
+ ^^^^^
+ sldjf
+ ^^^^^^^
+ lsdjjkf
+ ^^^^^^
+ sldkjf
+ ^^^^^^
+ lkjsfd
+ """
if not self.streamlined:
self.streamline()
for e in self.ignoreExprs:
@@ -1189,12 +1690,22 @@ class ParserElement(object): raise exc
def transformString( self, instring ):
- """Extension to C{L{scanString}}, to modify matching text with modified tokens that may
- be returned from a parse action. To use C{transformString}, define a grammar and
- attach a parse action to it that modifies the returned token list.
- Invoking C{transformString()} on a target string will then scan for matches,
- and replace the matched text patterns according to the logic in the parse
- action. C{transformString()} returns the resulting transformed string."""
+ """
+ Extension to C{L{scanString}}, to modify matching text with modified tokens that may
+ be returned from a parse action. To use C{transformString}, define a grammar and
+ attach a parse action to it that modifies the returned token list.
+ Invoking C{transformString()} on a target string will then scan for matches,
+ and replace the matched text patterns according to the logic in the parse
+ action. C{transformString()} returns the resulting transformed string.
+
+ Example::
+ wd = Word(alphas)
+ wd.setParseAction(lambda toks: toks[0].title())
+
+ print(wd.transformString("now is the winter of our discontent made glorious summer by this sun of york."))
+ Prints::
+ Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York.
+ """
out = []
lastE = 0
# force preservation of <TAB>s, to minimize unwanted transformation of string, and to
@@ -1222,9 +1733,18 @@ class ParserElement(object): raise exc
def searchString( self, instring, maxMatches=_MAX_INT ):
- """Another extension to C{L{scanString}}, simplifying the access to the tokens found
- to match the given parse expression. May be called with optional
- C{maxMatches} argument, to clip searching after 'n' matches are found.
+ """
+ Another extension to C{L{scanString}}, simplifying the access to the tokens found
+ to match the given parse expression. May be called with optional
+ C{maxMatches} argument, to clip searching after 'n' matches are found.
+
+ Example::
+ # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters
+ cap_word = Word(alphas.upper(), alphas.lower())
+
+ print(cap_word.searchString("More than Iron, more than Lead, more than Gold I need Electricity"))
+ prints::
+ ['More', 'Iron', 'Lead', 'Gold', 'I']
"""
try:
return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ])
@@ -1235,10 +1755,42 @@ class ParserElement(object): # catch and re-raise exception from here, clears out pyparsing internal stack trace
raise exc
+ def split(self, instring, maxsplit=_MAX_INT, includeSeparators=False):
+ """
+ Generator method to split a string using the given expression as a separator.
+ May be called with optional C{maxsplit} argument, to limit the number of splits;
+ and the optional C{includeSeparators} argument (default=C{False}), if the separating
+ matching text should be included in the split results.
+
+ Example::
+ punc = oneOf(list(".,;:/-!?"))
+ print(list(punc.split("This, this?, this sentence, is badly punctuated!")))
+ prints::
+ ['This', ' this', '', ' this sentence', ' is badly punctuated', '']
+ """
+ splits = 0
+ last = 0
+ for t,s,e in self.scanString(instring, maxMatches=maxsplit):
+ yield instring[last:s]
+ if includeSeparators:
+ yield t[0]
+ last = e
+ yield instring[last:]
+
def __add__(self, other ):
- """Implementation of + operator - returns C{L{And}}"""
+ """
+ Implementation of + operator - returns C{L{And}}. Adding strings to a ParserElement
+ converts them to L{Literal}s by default.
+
+ Example::
+ greet = Word(alphas) + "," + Word(alphas) + "!"
+ hello = "Hello, World!"
+ print (hello, "->", greet.parseString(hello))
+ Prints::
+ Hello, World! -> ['Hello', ',', 'World', '!']
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1246,9 +1798,11 @@ class ParserElement(object): return And( [ self, other ] )
def __radd__(self, other ):
- """Implementation of + operator when left operand is not a C{L{ParserElement}}"""
+ """
+ Implementation of + operator when left operand is not a C{L{ParserElement}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1256,9 +1810,11 @@ class ParserElement(object): return other + self
def __sub__(self, other):
- """Implementation of - operator, returns C{L{And}} with error stop"""
+ """
+ Implementation of - operator, returns C{L{And}} with error stop
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1266,9 +1822,11 @@ class ParserElement(object): return And( [ self, And._ErrorStop(), other ] )
def __rsub__(self, other ):
- """Implementation of - operator when left operand is not a C{L{ParserElement}}"""
+ """
+ Implementation of - operator when left operand is not a C{L{ParserElement}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1276,24 +1834,24 @@ class ParserElement(object): return other - self
def __mul__(self,other):
- """Implementation of * operator, allows use of C{expr * 3} in place of
- C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer
- tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples
- may also include C{None} as in:
- - C{expr*(n,None)} or C{expr*(n,)} is equivalent
+ """
+ Implementation of * operator, allows use of C{expr * 3} in place of
+ C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer
+ tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples
+ may also include C{None} as in:
+ - C{expr*(n,None)} or C{expr*(n,)} is equivalent
to C{expr*n + L{ZeroOrMore}(expr)}
(read as "at least n instances of C{expr}")
- - C{expr*(None,n)} is equivalent to C{expr*(0,n)}
+ - C{expr*(None,n)} is equivalent to C{expr*(0,n)}
(read as "0 to n instances of C{expr}")
- - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)}
- - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)}
-
- Note that C{expr*(None,n)} does not raise an exception if
- more than n exprs exist in the input stream; that is,
- C{expr*(None,n)} does not enforce a maximum number of expr
- occurrences. If this behavior is desired, then write
- C{expr*(None,n) + ~expr}
-
+ - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)}
+ - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)}
+
+ Note that C{expr*(None,n)} does not raise an exception if
+ more than n exprs exist in the input stream; that is,
+ C{expr*(None,n)} does not enforce a maximum number of expr
+ occurrences. If this behavior is desired, then write
+ C{expr*(None,n) + ~expr}
"""
if isinstance(other,int):
minElements, optElements = other,0
@@ -1347,9 +1905,11 @@ class ParserElement(object): return self.__mul__(other)
def __or__(self, other ):
- """Implementation of | operator - returns C{L{MatchFirst}}"""
+ """
+ Implementation of | operator - returns C{L{MatchFirst}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1357,9 +1917,11 @@ class ParserElement(object): return MatchFirst( [ self, other ] )
def __ror__(self, other ):
- """Implementation of | operator when left operand is not a C{L{ParserElement}}"""
+ """
+ Implementation of | operator when left operand is not a C{L{ParserElement}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1367,9 +1929,11 @@ class ParserElement(object): return other | self
def __xor__(self, other ):
- """Implementation of ^ operator - returns C{L{Or}}"""
+ """
+ Implementation of ^ operator - returns C{L{Or}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1377,9 +1941,11 @@ class ParserElement(object): return Or( [ self, other ] )
def __rxor__(self, other ):
- """Implementation of ^ operator when left operand is not a C{L{ParserElement}}"""
+ """
+ Implementation of ^ operator when left operand is not a C{L{ParserElement}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1387,9 +1953,11 @@ class ParserElement(object): return other ^ self
def __and__(self, other ):
- """Implementation of & operator - returns C{L{Each}}"""
+ """
+ Implementation of & operator - returns C{L{Each}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1397,9 +1965,11 @@ class ParserElement(object): return Each( [ self, other ] )
def __rand__(self, other ):
- """Implementation of & operator when left operand is not a C{L{ParserElement}}"""
+ """
+ Implementation of & operator when left operand is not a C{L{ParserElement}}
+ """
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
@@ -1407,41 +1977,49 @@ class ParserElement(object): return other & self
def __invert__( self ):
- """Implementation of ~ operator - returns C{L{NotAny}}"""
+ """
+ Implementation of ~ operator - returns C{L{NotAny}}
+ """
return NotAny( self )
def __call__(self, name=None):
- """Shortcut for C{L{setResultsName}}, with C{listAllMatches=default}::
- userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno")
- could be written as::
- userdata = Word(alphas)("name") + Word(nums+"-")("socsecno")
-
- If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be
- passed as C{True}.
+ """
+ Shortcut for C{L{setResultsName}}, with C{listAllMatches=False}.
+
+ If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be
+ passed as C{True}.
- If C{name} is omitted, same as calling C{L{copy}}.
- """
+ If C{name} is omitted, same as calling C{L{copy}}.
+
+ Example::
+ # these are equivalent
+ userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno")
+ userdata = Word(alphas)("name") + Word(nums+"-")("socsecno")
+ """
if name is not None:
return self.setResultsName(name)
else:
return self.copy()
def suppress( self ):
- """Suppresses the output of this C{ParserElement}; useful to keep punctuation from
- cluttering up returned output.
+ """
+ Suppresses the output of this C{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
- C{ParserElement}'s defined pattern. This is normally only used internally by
- the pyparsing module, but may be needed in some whitespace-sensitive grammars.
+ """
+ Disables the skipping of whitespace before matching the characters in the
+ C{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
+ """
+ Overrides the default whitespace chars
"""
self.skipWhitespace = True
self.whiteChars = chars
@@ -1449,26 +2027,41 @@ class ParserElement(object): return self
def parseWithTabs( self ):
- """Overrides default behavior to expand C{<TAB>}s to spaces before parsing the input string.
- Must be called before C{parseString} when the input grammar contains elements that
- match C{<TAB>} characters."""
+ """
+ Overrides default behavior to expand C{<TAB>}s to spaces before parsing the input string.
+ Must be called before C{parseString} when the input grammar contains elements that
+ match C{<TAB>} 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.
"""
+ Define expression to be ignored (e.g., comments) while doing pattern
+ matching; may be called repeatedly, to define multiple comment or other
+ ignorable patterns.
+
+ Example::
+ patt = OneOrMore(Word(alphas))
+ patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj']
+
+ patt.ignore(cStyleComment)
+ patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj', 'lskjd']
+ """
+ if isinstance(other, basestring):
+ other = Suppress(other)
+
if isinstance( other, Suppress ):
if other not in self.ignoreExprs:
- self.ignoreExprs.append( other.copy() )
+ self.ignoreExprs.append(other)
else:
self.ignoreExprs.append( Suppress( other.copy() ) )
return self
def setDebugActions( self, startAction, successAction, exceptionAction ):
- """Enable display of debugging messages while doing pattern matching."""
+ """
+ Enable display of debugging messages while doing pattern matching.
+ """
self.debugActions = (startAction or _defaultStartDebugAction,
successAction or _defaultSuccessDebugAction,
exceptionAction or _defaultExceptionDebugAction)
@@ -1476,8 +2069,40 @@ class ParserElement(object): return self
def setDebug( self, flag=True ):
- """Enable display of debugging messages while doing pattern matching.
- Set C{flag} to True to enable, False to disable."""
+ """
+ Enable display of debugging messages while doing pattern matching.
+ Set C{flag} to True to enable, False to disable.
+
+ Example::
+ wd = Word(alphas).setName("alphaword")
+ integer = Word(nums).setName("numword")
+ term = wd | integer
+
+ # turn on debugging for wd
+ wd.setDebug()
+
+ OneOrMore(term).parseString("abc 123 xyz 890")
+
+ prints::
+ Match alphaword at loc 0(1,1)
+ Matched alphaword -> ['abc']
+ Match alphaword at loc 3(1,4)
+ Exception raised:Expected alphaword (at char 4), (line:1, col:5)
+ Match alphaword at loc 7(1,8)
+ Matched alphaword -> ['xyz']
+ Match alphaword at loc 11(1,12)
+ Exception raised:Expected alphaword (at char 12), (line:1, col:13)
+ Match alphaword at loc 15(1,16)
+ Exception raised:Expected alphaword (at char 15), (line:1, col:16)
+
+ The output shown is that produced by the default debug actions - custom debug actions can be
+ specified using L{setDebugActions}. Prior to attempting
+ to match the C{wd} expression, the debugging message C{"Match <exprname> at loc <n>(<line>,<col>)"}
+ is shown. Then if the parse succeeds, a C{"Matched"} message is shown, or an C{"Exception raised"}
+ message is shown. Also note the use of L{setName} to assign a human-readable name to the expression,
+ which makes debugging and exception messages easier to understand - for instance, the default
+ name created for the C{Word} expression without calling C{setName} is C{"W:(ABCD...)"}.
+ """
if flag:
self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction )
else:
@@ -1499,20 +2124,22 @@ class ParserElement(object): pass
def validate( self, validateTrace=[] ):
- """Check defined expressions for valid structure, check for infinite recursive definitions."""
+ """
+ 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.
+ """
+ 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, "r")
- file_contents = f.read()
- f.close()
+ with open(file_or_filename, "r") as f:
+ file_contents = f.read()
try:
return self.parseString(file_contents, parseAll)
except ParseBaseException as exc:
@@ -1524,13 +2151,9 @@ class ParserElement(object): def __eq__(self,other):
if isinstance(other, ParserElement):
- return self is other or self.__dict__ == other.__dict__
+ return self is other or vars(self) == vars(other)
elif isinstance(other, basestring):
- try:
- self.parseString(_ustr(other), parseAll=True)
- return True
- except ParseBaseException:
- return False
+ return self.matches(other)
else:
return super(ParserElement,self)==other
@@ -1546,40 +2169,161 @@ class ParserElement(object): def __rne__(self,other):
return not (self == other)
- def runTests(self, tests, parseAll=False):
- """Execute the parse expression on a series of test strings, showing each
- test, the parsed results or where the parse failed. Quick and easy way to
- run a parse expression against a list of sample strings.
+ def matches(self, testString, parseAll=True):
+ """
+ Method for quick testing of a parser against a test string. Good for simple
+ inline microtests of sub expressions while building up larger parser.0
- Parameters:
- - tests - a list of separate test strings, or a multiline string of test strings
- - parseAll - (default=False) - flag to pass to C{L{parseString}} when running tests
+ Parameters:
+ - testString - to test against this expression for a match
+ - parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
+
+ Example::
+ expr = Word(nums)
+ assert expr.matches("100")
+ """
+ try:
+ self.parseString(_ustr(testString), parseAll=parseAll)
+ return True
+ except ParseBaseException:
+ return False
+
+ def runTests(self, tests, parseAll=True, comment='#', fullDump=True, printResults=True, failureTests=False):
+ """
+ Execute the parse expression on a series of test strings, showing each
+ test, the parsed results or where the parse failed. Quick and easy way to
+ run a parse expression against a list of sample strings.
+
+ Parameters:
+ - tests - a list of separate test strings, or a multiline string of test strings
+ - parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
+ - comment - (default=C{'#'}) - expression for indicating embedded comments in the test
+ string; pass None to disable comment filtering
+ - fullDump - (default=C{True}) - dump results as list followed by results names in nested outline;
+ if False, only dump nested list
+ - printResults - (default=C{True}) prints test output to stdout
+ - failureTests - (default=C{False}) indicates if these tests are expected to fail parsing
+
+ Returns: a (success, results) tuple, where success indicates that all tests succeeded
+ (or failed if C{failureTests} is True), and the results contain a list of lines of each
+ test's output
+
+ Example::
+ number_expr = pyparsing_common.number.copy()
+
+ result = number_expr.runTests('''
+ # unsigned integer
+ 100
+ # negative integer
+ -100
+ # float with scientific notation
+ 6.02e23
+ # integer with scientific notation
+ 1e-12
+ ''')
+ print("Success" if result[0] else "Failed!")
+
+ result = number_expr.runTests('''
+ # stray character
+ 100Z
+ # missing leading digit before '.'
+ -.100
+ # too many '.'
+ 3.14.159
+ ''', failureTests=True)
+ print("Success" if result[0] else "Failed!")
+ prints::
+ # unsigned integer
+ 100
+ [100]
+
+ # negative integer
+ -100
+ [-100]
+
+ # float with scientific notation
+ 6.02e23
+ [6.02e+23]
+
+ # integer with scientific notation
+ 1e-12
+ [1e-12]
+
+ Success
+
+ # stray character
+ 100Z
+ ^
+ FAIL: Expected end of text (at char 3), (line:1, col:4)
+
+ # missing leading digit before '.'
+ -.100
+ ^
+ FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1)
+
+ # too many '.'
+ 3.14.159
+ ^
+ FAIL: Expected end of text (at char 4), (line:1, col:5)
+
+ Success
"""
if isinstance(tests, basestring):
- tests = map(str.strip, tests.splitlines())
+ tests = list(map(str.strip, tests.rstrip().splitlines()))
+ if isinstance(comment, basestring):
+ comment = Literal(comment)
+ allResults = []
+ comments = []
+ success = True
for t in tests:
- out = [t]
+ if comment is not None and comment.matches(t, False) or comments and not t:
+ comments.append(t)
+ continue
+ if not t:
+ continue
+ out = ['\n'.join(comments), t]
+ comments = []
try:
- out.append(self.parseString(t, parseAll=parseAll).dump())
- except ParseException as pe:
+ result = self.parseString(t, parseAll=parseAll)
+ out.append(result.dump(full=fullDump))
+ success = success and not failureTests
+ except ParseBaseException as pe:
+ fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else ""
if '\n' in t:
out.append(line(pe.loc, t))
- out.append(' '*(col(pe.loc,t)-1) + '^')
+ out.append(' '*(col(pe.loc,t)-1) + '^' + fatal)
else:
- out.append(' '*pe.loc + '^')
- out.append(str(pe))
- out.append('')
- print('\n'.join(out))
+ out.append(' '*pe.loc + '^' + fatal)
+ out.append("FAIL: " + str(pe))
+ success = success and failureTests
+ result = pe
+ except Exception as exc:
+ out.append("FAIL-EXCEPTION: " + str(exc))
+ success = success and failureTests
+ result = exc
+
+ if printResults:
+ if fullDump:
+ out.append('')
+ print('\n'.join(out))
+
+ allResults.append((t, result))
+
+ return success, allResults
class Token(ParserElement):
- """Abstract C{ParserElement} subclass, for defining atomic matching patterns."""
+ """
+ Abstract C{ParserElement} subclass, for defining atomic matching patterns.
+ """
def __init__( self ):
super(Token,self).__init__( savelist=False )
class Empty(Token):
- """An empty token, will always match."""
+ """
+ An empty token, will always match.
+ """
def __init__( self ):
super(Empty,self).__init__()
self.name = "Empty"
@@ -1588,7 +2332,9 @@ class Empty(Token): class NoMatch(Token):
- """A token that will never match."""
+ """
+ A token that will never match.
+ """
def __init__( self ):
super(NoMatch,self).__init__()
self.name = "NoMatch"
@@ -1601,7 +2347,19 @@ class NoMatch(Token): class Literal(Token):
- """Token to exactly match a specified string."""
+ """
+ Token to exactly match a specified string.
+
+ Example::
+ Literal('blah').parseString('blah') # -> ['blah']
+ Literal('blah').parseString('blahfooblah') # -> ['blah']
+ Literal('blah').parseString('bla') # -> Exception: Expected "blah"
+
+ For case-insensitive matching, use L{CaselessLiteral}.
+
+ For keyword matching (force word break before and after the matched string),
+ use L{Keyword} or L{CaselessKeyword}.
+ """
def __init__( self, matchString ):
super(Literal,self).__init__()
self.match = matchString
@@ -1627,22 +2385,31 @@ class Literal(Token): return loc+self.matchLen, self.match
raise ParseException(instring, loc, self.errmsg, self)
_L = Literal
-ParserElement.literalStringClass = Literal
+ParserElement._literalStringClass = 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 C{L{Literal}}::
- Literal("if") will match the leading C{'if'} in C{'ifAndOnlyIf'}.
- Keyword("if") will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'}
- Accepts two optional constructor arguments in addition to the keyword string:
- C{identChars} is a string of characters that would be valid identifier characters,
- defaulting to all alphanumerics + "_" and "$"; C{caseless} allows case-insensitive
- matching, default is C{False}.
+ """
+ Token to exactly match a specified string as a keyword, that is, it must be
+ immediately followed by a non-keyword character. Compare with C{L{Literal}}:
+ - C{Literal("if")} will match the leading C{'if'} in C{'ifAndOnlyIf'}.
+ - C{Keyword("if")} will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'}
+ Accepts two optional constructor arguments in addition to the keyword string:
+ - C{identChars} is a string of characters that would be valid identifier characters,
+ defaulting to all alphanumerics + "_" and "$"
+ - C{caseless} allows case-insensitive matching, default is C{False}.
+
+ Example::
+ Keyword("start").parseString("start") # -> ['start']
+ Keyword("start").parseString("starting") # -> Exception
+
+ For case-insensitive matching, use L{CaselessKeyword}.
"""
DEFAULT_KEYWORD_CHARS = alphanums+"_$"
- def __init__( self, matchString, identChars=DEFAULT_KEYWORD_CHARS, caseless=False ):
+ def __init__( self, matchString, identChars=None, caseless=False ):
super(Keyword,self).__init__()
+ if identChars is None:
+ identChars = Keyword.DEFAULT_KEYWORD_CHARS
self.match = matchString
self.matchLen = len(matchString)
try:
@@ -1686,9 +2453,15 @@ class Keyword(Token): Keyword.DEFAULT_KEYWORD_CHARS = chars
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.
+ """
+ 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.
+
+ Example::
+ OneOrMore(CaselessLiteral("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD', 'CMD']
+
+ (Contrast with example for L{CaselessKeyword}.)
"""
def __init__( self, matchString ):
super(CaselessLiteral,self).__init__( matchString.upper() )
@@ -1703,7 +2476,15 @@ class CaselessLiteral(Literal): raise ParseException(instring, loc, self.errmsg, self)
class CaselessKeyword(Keyword):
- def __init__( self, matchString, identChars=Keyword.DEFAULT_KEYWORD_CHARS ):
+ """
+ Caseless version of L{Keyword}.
+
+ Example::
+ OneOrMore(CaselessKeyword("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD']
+
+ (Contrast with example for L{CaselessLiteral}.)
+ """
+ def __init__( self, matchString, identChars=None ):
super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True )
def parseImpl( self, instring, loc, doActions=True ):
@@ -1712,17 +2493,113 @@ class CaselessKeyword(Keyword): return loc+self.matchLen, self.match
raise ParseException(instring, loc, self.errmsg, self)
+class CloseMatch(Token):
+ """
+ A variation on L{Literal} which matches "close" matches, that is,
+ strings with at most 'n' mismatching characters. C{CloseMatch} takes parameters:
+ - C{match_string} - string to be matched
+ - C{maxMismatches} - (C{default=1}) maximum number of mismatches allowed to count as a match
+
+ The results from a successful parse will contain the matched text from the input string and the following named results:
+ - C{mismatches} - a list of the positions within the match_string where mismatches were found
+ - C{original} - the original match_string used to compare against the input string
+
+ If C{mismatches} is an empty list, then the match was an exact match.
+
+ Example::
+ patt = CloseMatch("ATCATCGAATGGA")
+ patt.parseString("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']})
+ patt.parseString("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1)
+
+ # exact match
+ patt.parseString("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']})
+
+ # close match allowing up to 2 mismatches
+ patt = CloseMatch("ATCATCGAATGGA", maxMismatches=2)
+ patt.parseString("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']})
+ """
+ def __init__(self, match_string, maxMismatches=1):
+ super(CloseMatch,self).__init__()
+ self.name = match_string
+ self.match_string = match_string
+ self.maxMismatches = maxMismatches
+ self.errmsg = "Expected %r (with up to %d mismatches)" % (self.match_string, self.maxMismatches)
+ self.mayIndexError = False
+ self.mayReturnEmpty = False
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ start = loc
+ instrlen = len(instring)
+ maxloc = start + len(self.match_string)
+
+ if maxloc <= instrlen:
+ match_string = self.match_string
+ match_stringloc = 0
+ mismatches = []
+ maxMismatches = self.maxMismatches
+
+ for match_stringloc,s_m in enumerate(zip(instring[loc:maxloc], self.match_string)):
+ src,mat = s_m
+ if src != mat:
+ mismatches.append(match_stringloc)
+ if len(mismatches) > maxMismatches:
+ break
+ else:
+ loc = match_stringloc + 1
+ results = ParseResults([instring[start:loc]])
+ results['original'] = self.match_string
+ results['mismatches'] = mismatches
+ return loc, results
+
+ raise ParseException(instring, loc, self.errmsg, self)
+
+
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 C{min} is 1 (a
- minimum value < 1 is not valid); the default values for C{max} and C{exact}
- are 0, meaning no maximum or exact length restriction. An optional
- C{exclude} parameter can list characters that might be found in
- the input C{bodyChars} string; useful to define a word of all printables
- except for one or two characters, for instance.
+ """
+ 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 C{min} is 1 (a
+ minimum value < 1 is not valid); the default values for C{max} and C{exact}
+ are 0, meaning no maximum or exact length restriction. An optional
+ C{excludeChars} parameter can list characters that might be found in
+ the input C{bodyChars} string; useful to define a word of all printables
+ except for one or two characters, for instance.
+
+ L{srange} is useful for defining custom character set strings for defining
+ C{Word} expressions, using range notation from regular expression character sets.
+
+ A common mistake is to use C{Word} to match a specific literal string, as in
+ C{Word("Address")}. Remember that C{Word} uses the string argument to define
+ I{sets} of matchable characters. This expression would match "Add", "AAA",
+ "dAred", or any other word made up of the characters 'A', 'd', 'r', 'e', and 's'.
+ To match an exact literal string, use L{Literal} or L{Keyword}.
+
+ pyparsing includes helper strings for building Words:
+ - L{alphas}
+ - L{nums}
+ - L{alphanums}
+ - L{hexnums}
+ - L{alphas8bit} (alphabetic characters in ASCII range 128-255 - accented, tilded, umlauted, etc.)
+ - L{punc8bit} (non-alphabetic characters in ASCII range 128-255 - currency, symbols, superscripts, diacriticals, etc.)
+ - L{printables} (any non-whitespace character)
+
+ Example::
+ # a word composed of digits
+ integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9"))
+
+ # a word with a leading capital, and zero or more lowercase
+ capital_word = Word(alphas.upper(), alphas.lower())
+
+ # hostnames are alphanumeric, with leading alpha, and '-'
+ hostname = Word(alphas, alphanums+'-')
+
+ # roman numeral (not a strict parser, accepts invalid mix of characters)
+ roman = Word("IVXLCDM")
+
+ # any string of non-whitespace characters, except for ','
+ csv_value = Word(printables, excludeChars=",")
"""
def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ):
super(Word,self).__init__()
@@ -1837,8 +2714,17 @@ class Word(Token): 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.
+ """
+ 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.
+ If the given regex contains named groups (defined using C{(?P<name>...)}), these will be preserved as
+ named parse results.
+
+ Example::
+ realnum = Regex(r"[+-]?\d+\.\d*")
+ date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)')
+ # ref: http://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression
+ roman = Regex(r"M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})")
"""
compiledREtype = type(re.compile("[A-Z]"))
def __init__( self, pattern, flags=0):
@@ -1846,7 +2732,7 @@ class Regex(Token): super(Regex,self).__init__()
if isinstance(pattern, basestring):
- if len(pattern) == 0:
+ if not pattern:
warnings.warn("null string passed to Regex; use Empty() instead",
SyntaxWarning, stacklevel=2)
@@ -1901,23 +2787,36 @@ class Regex(Token): class QuotedString(Token):
- """Token for matching strings that are delimited by quoting characters.
+ r"""
+ Token for matching strings that are delimited by quoting characters.
+
+ 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=C{None})
+ - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=C{None})
+ - multiline - boolean indicating whether quotes can span multiple lines (default=C{False})
+ - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True})
+ - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar)
+ - convertWhitespaceEscapes - convert escaped whitespace (C{'\t'}, C{'\n'}, etc.) to actual whitespace (default=C{True})
+
+ Example::
+ qs = QuotedString('"')
+ print(qs.searchString('lsjdf "This is the quote" sldjf'))
+ complex_qs = QuotedString('{{', endQuoteChar='}}')
+ print(complex_qs.searchString('lsjdf {{This is the "quote"}} sldjf'))
+ sql_qs = QuotedString('"', escQuote='""')
+ print(sql_qs.searchString('lsjdf "This is the quote with ""embedded"" quotes" sldjf'))
+ prints::
+ [['This is the quote']]
+ [['This is the "quote"']]
+ [['This is the quote with "embedded" quotes']]
"""
- 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=C{False})
- - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True})
- - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar)
- """
+ def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None, convertWhitespaceEscapes=True):
super(QuotedString,self).__init__()
# remove white space from quote chars - wont work anyway
quoteChar = quoteChar.strip()
- if len(quoteChar) == 0:
+ if not quoteChar:
warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
raise SyntaxError()
@@ -1925,7 +2824,7 @@ class QuotedString(Token): endQuoteChar = quoteChar
else:
endQuoteChar = endQuoteChar.strip()
- if len(endQuoteChar) == 0:
+ if not endQuoteChar:
warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
raise SyntaxError()
@@ -1937,6 +2836,7 @@ class QuotedString(Token): self.escChar = escChar
self.escQuote = escQuote
self.unquoteResults = unquoteResults
+ self.convertWhitespaceEscapes = convertWhitespaceEscapes
if multiline:
self.flags = re.MULTILINE | re.DOTALL
@@ -1990,6 +2890,17 @@ class QuotedString(Token): ret = ret[self.quoteCharLen:-self.endQuoteCharLen]
if isinstance(ret,basestring):
+ # replace escaped whitespace
+ if '\\' in ret and self.convertWhitespaceEscapes:
+ ws_map = {
+ r'\t' : '\t',
+ r'\n' : '\n',
+ r'\f' : '\f',
+ r'\r' : '\r',
+ }
+ for wslit,wschar in ws_map.items():
+ ret = ret.replace(wslit, wschar)
+
# replace escaped characters
if self.escChar:
ret = re.sub(self.escCharReplacePattern,"\g<1>",ret)
@@ -2013,11 +2924,20 @@ class QuotedString(Token): 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 C{min} is 1 (a
- minimum value < 1 is not valid); the default values for C{max} and C{exact}
- are 0, meaning no maximum or exact length restriction.
+ """
+ Token for matching words composed of characters I{not} in a given set (will
+ include whitespace in matched characters if not listed in the provided exclusion set - see example).
+ Defined with string containing all disallowed characters, and an optional
+ minimum, maximum, and/or exact length. The default value for C{min} is 1 (a
+ minimum value < 1 is not valid); the default values for C{max} and C{exact}
+ are 0, meaning no maximum or exact length restriction.
+
+ Example::
+ # define a comma-separated-value as anything that is not a ','
+ csv_value = CharsNotIn(',')
+ print(delimitedList(csv_value).parseString("dkls,lsdkjf,s12 34,@!#,213"))
+ prints::
+ ['dkls', 'lsdkjf', 's12 34', '@!#', '213']
"""
def __init__( self, notChars, min=1, max=0, exact=0 ):
super(CharsNotIn,self).__init__()
@@ -2075,11 +2995,13 @@ class CharsNotIn(Token): 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 C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments,
- as defined for the C{L{Word}} class."""
+ """
+ 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 C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments,
+ as defined for the C{L{Word}} class.
+ """
whiteStrs = {
" " : "<SPC>",
"\t": "<TAB>",
@@ -2131,7 +3053,9 @@ class _PositionToken(Token): self.mayIndexError = False
class GoToColumn(_PositionToken):
- """Token to advance to a specific column of input text; useful for tabular report scraping."""
+ """
+ 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
@@ -2154,7 +3078,9 @@ class GoToColumn(_PositionToken): return newloc, ret
class LineStart(_PositionToken):
- """Matches if current position is at the beginning of a line within the parse string"""
+ """
+ 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","") )
@@ -2174,7 +3100,9 @@ class LineStart(_PositionToken): return loc, []
class LineEnd(_PositionToken):
- """Matches if current position is at the end of a line within the parse string"""
+ """
+ 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","") )
@@ -2192,7 +3120,9 @@ class LineEnd(_PositionToken): raise ParseException(instring, loc, self.errmsg, self)
class StringStart(_PositionToken):
- """Matches if current position is at the beginning of the parse string"""
+ """
+ Matches if current position is at the beginning of the parse string
+ """
def __init__( self ):
super(StringStart,self).__init__()
self.errmsg = "Expected start of text"
@@ -2205,7 +3135,9 @@ class StringStart(_PositionToken): return loc, []
class StringEnd(_PositionToken):
- """Matches if current position is at the end of the parse string"""
+ """
+ Matches if current position is at the end of the parse string
+ """
def __init__( self ):
super(StringEnd,self).__init__()
self.errmsg = "Expected end of text"
@@ -2221,11 +3153,12 @@ class StringEnd(_PositionToken): raise ParseException(instring, loc, self.errmsg, self)
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 C{wordChars}
- (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
- use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of
- the string being parsed, or at the beginning of a line.
+ """
+ Matches if the current position is at the beginning of a Word, and
+ is not preceded by any character in a given set of C{wordChars}
+ (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
+ use C{WordStart(alphanums)}. C{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__()
@@ -2240,11 +3173,12 @@ class WordStart(_PositionToken): 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 C{wordChars}
- (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
- use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of
- the string being parsed, or at the end of a line.
+ """
+ Matches if the current position is at the end of a Word, and
+ is not followed by any character in a given set of C{wordChars}
+ (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
+ use C{WordEnd(alphanums)}. C{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__()
@@ -2262,18 +3196,21 @@ class WordEnd(_PositionToken): class ParseExpression(ParserElement):
- """Abstract subclass of ParserElement, for combining and post-processing parsed tokens."""
+ """
+ Abstract subclass of ParserElement, for combining and post-processing parsed tokens.
+ """
def __init__( self, exprs, savelist = False ):
super(ParseExpression,self).__init__(savelist)
if isinstance( exprs, _generatorType ):
exprs = list(exprs)
if isinstance( exprs, basestring ):
- self.exprs = [ Literal( exprs ) ]
- elif isinstance( exprs, collections.Sequence ):
+ self.exprs = [ ParserElement._literalStringClass( exprs ) ]
+ elif isinstance( exprs, collections.Iterable ):
+ exprs = list(exprs)
# if sequence of strings provided, wrap with Literal
if all(isinstance(expr, basestring) for expr in exprs):
- exprs = map(Literal, exprs)
+ exprs = map(ParserElement._literalStringClass, exprs)
self.exprs = list(exprs)
else:
try:
@@ -2351,7 +3288,7 @@ class ParseExpression(ParserElement): self.mayReturnEmpty |= other.mayReturnEmpty
self.mayIndexError |= other.mayIndexError
- self.errmsg = "Expected " + str(self)
+ self.errmsg = "Expected " + _ustr(self)
return self
@@ -2371,9 +3308,19 @@ class ParseExpression(ParserElement): return ret
class And(ParseExpression):
- """Requires all given C{ParseExpression}s to be found in the given order.
- Expressions may be separated by whitespace.
- May be constructed using the C{'+'} operator.
+ """
+ Requires all given C{ParseExpression}s to be found in the given order.
+ Expressions may be separated by whitespace.
+ May be constructed using the C{'+'} operator.
+ May also be constructed using the C{'-'} operator, which will suppress backtracking.
+
+ Example::
+ integer = Word(nums)
+ name_expr = OneOrMore(Word(alphas))
+
+ expr = And([integer("id"),name_expr("name"),integer("age")])
+ # more easily written as:
+ expr = integer("id") + name_expr("name") + integer("age")
"""
class _ErrorStop(Empty):
@@ -2405,9 +3352,9 @@ class And(ParseExpression): raise
except ParseBaseException as pe:
pe.__traceback__ = None
- raise ParseSyntaxException(pe)
+ raise ParseSyntaxException._from_exception(pe)
except IndexError:
- raise ParseSyntaxException( ParseException(instring, len(instring), self.errmsg, self) )
+ raise ParseSyntaxException(instring, len(instring), self.errmsg, self)
else:
loc, exprtokens = e._parse( instring, loc, doActions )
if exprtokens or exprtokens.haskeys():
@@ -2416,7 +3363,7 @@ class And(ParseExpression): def __iadd__(self, other ):
if isinstance( other, basestring ):
- other = Literal( other )
+ other = ParserElement._literalStringClass( other )
return self.append( other ) #And( [ self, other ] )
def checkRecursion( self, parseElementList ):
@@ -2437,9 +3384,18 @@ class And(ParseExpression): class Or(ParseExpression):
- """Requires that at least one C{ParseExpression} is found.
- If two expressions match, the expression that matches the longest string will be used.
- May be constructed using the C{'^'} operator.
+ """
+ Requires that at least one C{ParseExpression} is found.
+ If two expressions match, the expression that matches the longest string will be used.
+ May be constructed using the C{'^'} operator.
+
+ Example::
+ # construct Or using '^' operator
+
+ number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums))
+ print(number.searchString("123 3.1416 789"))
+ prints::
+ [['123'], ['3.1416'], ['789']]
"""
def __init__( self, exprs, savelist = False ):
super(Or,self).__init__(exprs, savelist)
@@ -2488,7 +3444,7 @@ class Or(ParseExpression): def __ixor__(self, other ):
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
return self.append( other ) #Or( [ self, other ] )
def __str__( self ):
@@ -2507,9 +3463,21 @@ class Or(ParseExpression): class MatchFirst(ParseExpression):
- """Requires that at least one C{ParseExpression} is found.
- If two expressions match, the first one listed is the one that will match.
- May be constructed using the C{'|'} operator.
+ """
+ Requires that at least one C{ParseExpression} is found.
+ If two expressions match, the first one listed is the one that will match.
+ May be constructed using the C{'|'} operator.
+
+ Example::
+ # construct MatchFirst using '|' operator
+
+ # watch the order of expressions to match
+ number = Word(nums) | Combine(Word(nums) + '.' + Word(nums))
+ print(number.searchString("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']]
+
+ # put more selective expression first
+ number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums)
+ print(number.searchString("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']]
"""
def __init__( self, exprs, savelist = False ):
super(MatchFirst,self).__init__(exprs, savelist)
@@ -2544,7 +3512,7 @@ class MatchFirst(ParseExpression): def __ior__(self, other ):
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass( other )
+ other = ParserElement._literalStringClass( other )
return self.append( other ) #MatchFirst( [ self, other ] )
def __str__( self ):
@@ -2563,9 +3531,58 @@ class MatchFirst(ParseExpression): class Each(ParseExpression):
- """Requires all given C{ParseExpression}s to be found, but in any order.
- Expressions may be separated by whitespace.
- May be constructed using the C{'&'} operator.
+ """
+ Requires all given C{ParseExpression}s to be found, but in any order.
+ Expressions may be separated by whitespace.
+ May be constructed using the C{'&'} operator.
+
+ Example::
+ color = oneOf("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN")
+ shape_type = oneOf("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON")
+ integer = Word(nums)
+ shape_attr = "shape:" + shape_type("shape")
+ posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn")
+ color_attr = "color:" + color("color")
+ size_attr = "size:" + integer("size")
+
+ # use Each (using operator '&') to accept attributes in any order
+ # (shape and posn are required, color and size are optional)
+ shape_spec = shape_attr & posn_attr & Optional(color_attr) & Optional(size_attr)
+
+ shape_spec.runTests('''
+ shape: SQUARE color: BLACK posn: 100, 120
+ shape: CIRCLE size: 50 color: BLUE posn: 50,80
+ color:GREEN size:20 shape:TRIANGLE posn:20,40
+ '''
+ )
+ prints::
+ shape: SQUARE color: BLACK posn: 100, 120
+ ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']]
+ - color: BLACK
+ - posn: ['100', ',', '120']
+ - x: 100
+ - y: 120
+ - shape: SQUARE
+
+
+ shape: CIRCLE size: 50 color: BLUE posn: 50,80
+ ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']]
+ - color: BLUE
+ - posn: ['50', ',', '80']
+ - x: 50
+ - y: 80
+ - shape: CIRCLE
+ - size: 50
+
+
+ color: GREEN size: 20 shape: TRIANGLE posn: 20,40
+ ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']]
+ - color: GREEN
+ - posn: ['20', ',', '40']
+ - x: 20
+ - y: 40
+ - shape: TRIANGLE
+ - size: 20
"""
def __init__( self, exprs, savelist = True ):
super(Each,self).__init__(exprs, savelist)
@@ -2619,17 +3636,7 @@ class Each(ParseExpression): 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:
- tmp = ParseResults(finalResults[k])
- tmp += ParseResults(r[k])
- dups[k] = tmp
- finalResults += ParseResults(r)
- for k,v in dups.items():
- finalResults[k] = v
+ finalResults = sum(resultlist, ParseResults([]))
return loc, finalResults
def __str__( self ):
@@ -2648,11 +3655,16 @@ class Each(ParseExpression): class ParseElementEnhance(ParserElement):
- """Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens."""
+ """
+ Abstract subclass of C{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)
+ if issubclass(ParserElement._literalStringClass, Token):
+ expr = ParserElement._literalStringClass(expr)
+ else:
+ expr = ParserElement._literalStringClass(Literal(expr))
self.expr = expr
self.strRepr = None
if expr is not None:
@@ -2720,10 +3732,22 @@ class ParseElementEnhance(ParserElement): class FollowedBy(ParseElementEnhance):
- """Lookahead matching of the given parse expression. C{FollowedBy}
- does *not* advance the parsing position within the input string, it only
+ """
+ Lookahead matching of the given parse expression. C{FollowedBy}
+ does I{not} advance the parsing position within the input string, it only
verifies that the specified parse expression matches at the current
- position. C{FollowedBy} always returns a null token list."""
+ position. C{FollowedBy} always returns a null token list.
+
+ Example::
+ # use FollowedBy to match a label only if it is followed by a ':'
+ data_word = Word(alphas)
+ label = data_word + FollowedBy(':')
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+
+ OneOrMore(attr_expr).parseString("shape: SQUARE color: BLACK posn: upper left").pprint()
+ prints::
+ [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']]
+ """
def __init__( self, expr ):
super(FollowedBy,self).__init__(expr)
self.mayReturnEmpty = True
@@ -2734,11 +3758,16 @@ class FollowedBy(ParseElementEnhance): class NotAny(ParseElementEnhance):
- """Lookahead to disallow matching with the given parse expression. C{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, C{NotAny} does *not* skip over leading whitespace. C{NotAny}
- always returns a null token list. May be constructed using the '~' operator."""
+ """
+ Lookahead to disallow matching with the given parse expression. C{NotAny}
+ does I{not} advance the parsing position within the input string, it only
+ verifies that the specified parse expression does I{not} match at the current
+ position. Also, C{NotAny} does I{not} skip over leading whitespace. C{NotAny}
+ always returns a null token list. May be constructed using the '~' operator.
+
+ Example::
+
+ """
def __init__( self, expr ):
super(NotAny,self).__init__(expr)
#~ self.leaveWhitespace()
@@ -2747,11 +3776,7 @@ class NotAny(ParseElementEnhance): self.errmsg = "Found unwanted token, "+_ustr(self.expr)
def parseImpl( self, instring, loc, doActions=True ):
- try:
- self.expr.tryParse( instring, loc )
- except (ParseException,IndexError):
- pass
- else:
+ if self.expr.canParseNext(instring, loc):
raise ParseException(instring, loc, self.errmsg, self)
return loc, []
@@ -2764,80 +3789,114 @@ class NotAny(ParseElementEnhance): 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
+class _MultipleMatch(ParseElementEnhance):
+ def __init__( self, expr, stopOn=None):
+ super(_MultipleMatch, self).__init__(expr)
+ ender = stopOn
+ if isinstance(ender, basestring):
+ ender = ParserElement._literalStringClass(ender)
+ self.not_ender = ~ender if ender is not None else None
def parseImpl( self, instring, loc, doActions=True ):
- tokens = []
+ self_expr_parse = self.expr._parse
+ self_skip_ignorables = self._skipIgnorables
+ check_ender = self.not_ender is not None
+ if check_ender:
+ try_not_ender = self.not_ender.tryParse
+
+ # must be at least one (but first see if we are the stopOn sentinel;
+ # if so, fail)
+ if check_ender:
+ try_not_ender(instring, loc)
+ loc, tokens = self_expr_parse( instring, loc, doActions, callPreParse=False )
try:
- loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False )
- hasIgnoreExprs = ( len(self.ignoreExprs) > 0 )
+ hasIgnoreExprs = (not not self.ignoreExprs)
while 1:
+ if check_ender:
+ try_not_ender(instring, loc)
if hasIgnoreExprs:
- preloc = self._skipIgnorables( instring, loc )
+ preloc = self_skip_ignorables( instring, loc )
else:
preloc = loc
- loc, tmptokens = self.expr._parse( instring, preloc, doActions )
+ loc, tmptokens = self_expr_parse( instring, preloc, doActions )
if tmptokens or tmptokens.haskeys():
tokens += tmptokens
except (ParseException,IndexError):
pass
return loc, tokens
+
+class OneOrMore(_MultipleMatch):
+ """
+ Repetition of one or more of the given expression.
+
+ Parameters:
+ - expr - expression that must match one or more times
+ - stopOn - (default=C{None}) - expression for a terminating sentinel
+ (only required if the sentinel would ordinarily match the repetition
+ expression)
+
+ Example::
+ data_word = Word(alphas)
+ label = data_word + FollowedBy(':')
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
+
+ text = "shape: SQUARE posn: upper left color: BLACK"
+ OneOrMore(attr_expr).parseString(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']]
+
+ # use stopOn attribute for OneOrMore to avoid reading label string as part of the data
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+ OneOrMore(attr_expr).parseString(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']]
+
+ # could also be written as
+ (attr_expr * (1,)).parseString(text).pprint()
+ """
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
- self.strRepr = "[" + _ustr(self.expr) + "]..."
+ self.strRepr = "{" + _ustr(self.expr) + "}..."
return self.strRepr
def setResultsName( self, name, listAllMatches=False ):
- ret = super(ZeroOrMore,self).setResultsName(name,listAllMatches)
+ ret = super(OneOrMore,self).setResultsName(name,listAllMatches)
ret.saveAsList = True
return ret
+class ZeroOrMore(_MultipleMatch):
+ """
+ Optional repetition of zero or more of the given expression.
+
+ Parameters:
+ - expr - expression that must match zero or more times
+ - stopOn - (default=C{None}) - expression for a terminating sentinel
+ (only required if the sentinel would ordinarily match the repetition
+ expression)
-class OneOrMore(ParseElementEnhance):
- """Repetition of one or more of the given expression."""
+ Example: similar to L{OneOrMore}
+ """
+ def __init__( self, expr, stopOn=None):
+ super(ZeroOrMore,self).__init__(expr, stopOn=stopOn)
+ self.mayReturnEmpty = True
+
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.haskeys():
- tokens += tmptokens
+ return super(ZeroOrMore, self).parseImpl(instring, loc, doActions)
except (ParseException,IndexError):
- pass
-
- return loc, tokens
+ return loc, []
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
- self.strRepr = "{" + _ustr(self.expr) + "}..."
+ 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
@@ -2847,9 +3906,39 @@ class _NullToken(object): _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.
+ """
+ Optional matching of the given expression.
+
+ Parameters:
+ - expr - expression that must match zero or more times
+ - default (optional) - value to be returned if the optional expression is not found.
+
+ Example::
+ # US postal code can be a 5-digit zip, plus optional 4-digit qualifier
+ zip = Combine(Word(nums, exact=5) + Optional('-' + Word(nums, exact=4)))
+ zip.runTests('''
+ # traditional ZIP code
+ 12345
+
+ # ZIP+4 form
+ 12101-0001
+
+ # invalid ZIP
+ 98765-
+ ''')
+ prints::
+ # traditional ZIP code
+ 12345
+ ['12345']
+
+ # ZIP+4 form
+ 12101-0001
+ ['12101-0001']
+
+ # invalid ZIP
+ 98765-
+ ^
+ FAIL: Expected end of text (at char 5), (line:1, col:6)
"""
def __init__( self, expr, default=_optionalNotMatched ):
super(Optional,self).__init__( expr, savelist=False )
@@ -2879,13 +3968,60 @@ class Optional(ParseElementEnhance): return self.strRepr
-
class SkipTo(ParseElementEnhance):
- """Token for skipping over all undefined text until the matched expression is found.
- If C{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 C{ignore}
- argument is used to define grammars (typically quoted strings and comments) that
- might contain false matches.
+ """
+ Token for skipping over all undefined text until the matched expression is found.
+
+ Parameters:
+ - expr - target expression marking the end of the data to be skipped
+ - include - (default=C{False}) if True, the target expression is also parsed
+ (the skipped text and target expression are returned as a 2-element list).
+ - ignore - (default=C{None}) used to define grammars (typically quoted strings and
+ comments) that might contain false matches to the target expression
+ - failOn - (default=C{None}) define expressions that are not allowed to be
+ included in the skipped test; if found before the target expression is found,
+ the SkipTo is not a match
+
+ Example::
+ report = '''
+ Outstanding Issues Report - 1 Jan 2000
+
+ # | Severity | Description | Days Open
+ -----+----------+-------------------------------------------+-----------
+ 101 | Critical | Intermittent system crash | 6
+ 94 | Cosmetic | Spelling error on Login ('log|n') | 14
+ 79 | Minor | System slow when running too many reports | 47
+ '''
+ integer = Word(nums)
+ SEP = Suppress('|')
+ # use SkipTo to simply match everything up until the next SEP
+ # - ignore quoted strings, so that a '|' character inside a quoted string does not match
+ # - parse action will call token.strip() for each matched token, i.e., the description body
+ string_data = SkipTo(SEP, ignore=quotedString)
+ string_data.setParseAction(tokenMap(str.strip))
+ ticket_expr = (integer("issue_num") + SEP
+ + string_data("sev") + SEP
+ + string_data("desc") + SEP
+ + integer("days_open"))
+
+ for tkt in ticket_expr.searchString(report):
+ print tkt.dump()
+ prints::
+ ['101', 'Critical', 'Intermittent system crash', '6']
+ - days_open: 6
+ - desc: Intermittent system crash
+ - issue_num: 101
+ - sev: Critical
+ ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14']
+ - days_open: 14
+ - desc: Spelling error on Login ('log|n')
+ - issue_num: 94
+ - sev: Cosmetic
+ ['79', 'Minor', 'System slow when running too many reports', '47']
+ - days_open: 47
+ - desc: System slow when running too many reports
+ - issue_num: 79
+ - sev: Minor
"""
def __init__( self, other, include=False, ignore=None, failOn=None ):
super( SkipTo, self ).__init__( other )
@@ -2894,77 +4030,85 @@ class SkipTo(ParseElementEnhance): self.mayIndexError = False
self.includeMatch = include
self.asList = False
- if failOn is not None and isinstance(failOn, basestring):
- self.failOn = Literal(failOn)
+ if isinstance(failOn, basestring):
+ self.failOn = ParserElement._literalStringClass(failOn)
else:
self.failOn = failOn
self.errmsg = "No match found for "+_ustr(self.expr)
def parseImpl( self, instring, loc, doActions=True ):
- startLoc = loc
+ startloc = loc
instrlen = len(instring)
expr = self.expr
- failParse = False
- while loc <= instrlen:
- try:
- if self.failOn:
+ expr_parse = self.expr._parse
+ self_failOn_canParseNext = self.failOn.canParseNext if self.failOn is not None else None
+ self_ignoreExpr_tryParse = self.ignoreExpr.tryParse if self.ignoreExpr is not None else None
+
+ tmploc = loc
+ while tmploc <= instrlen:
+ if self_failOn_canParseNext is not None:
+ # break if failOn expression matches
+ if self_failOn_canParseNext(instring, tmploc):
+ break
+
+ if self_ignoreExpr_tryParse is not None:
+ # advance past ignore expressions
+ while 1:
try:
- self.failOn.tryParse(instring, loc)
+ tmploc = self_ignoreExpr_tryParse(instring, tmploc)
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
- raise ParseException(instring, loc, self.errmsg, self)
+ break
+
+ try:
+ expr_parse(instring, tmploc, doActions=False, callPreParse=False)
+ except (ParseException, IndexError):
+ # no match, advance loc in string
+ tmploc += 1
+ else:
+ # matched skipto expr, done
+ break
+
+ else:
+ # ran off the end of the input string without matching skipto expr, fail
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ # build up return values
+ loc = tmploc
+ skiptext = instring[startloc:loc]
+ skipresult = ParseResults(skiptext)
+
+ if self.includeMatch:
+ loc, mat = expr_parse(instring,loc,doActions,callPreParse=False)
+ skipresult += mat
+
+ return loc, skipresult
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 C{Forward} variable using the '<<' operator.
-
- Note: take care when assigning to C{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 C{Forward}::
- fwdExpr << (a | b | c)
- Converting to use the '<<=' operator instead will avoid this problem.
+ """
+ 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 C{Forward} variable using the '<<' operator.
+
+ Note: take care when assigning to C{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 C{Forward}::
+ fwdExpr << (a | b | c)
+ Converting to use the '<<=' operator instead will avoid this problem.
+
+ See L{ParseResults.pprint} for an example of a recursive parser created using
+ C{Forward}.
"""
def __init__( self, other=None ):
super(Forward,self).__init__( other, savelist=False )
def __lshift__( self, other ):
if isinstance( other, basestring ):
- other = ParserElement.literalStringClass(other)
+ other = ParserElement._literalStringClass(other)
self.expr = other
- self.mayReturnEmpty = other.mayReturnEmpty
self.strRepr = None
self.mayIndexError = self.expr.mayIndexError
self.mayReturnEmpty = self.expr.mayReturnEmpty
@@ -2998,7 +4142,9 @@ class Forward(ParseElementEnhance): def __str__( self ):
if hasattr(self,"name"):
return self.name
+ return self.__class__.__name__ + ": ..."
+ # stubbed out for now - creates awful memory and perf issues
self._revertClass = self.__class__
self.__class__ = _ForwardNoRecurse
try:
@@ -3023,26 +4169,29 @@ class _ForwardNoRecurse(Forward): return "..."
class TokenConverter(ParseElementEnhance):
- """Abstract subclass of C{ParseExpression}, for converting parsed results."""
+ """
+ Abstract subclass of C{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( str.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 C{'adjacent=False'} in the constructor.
+ """
+ 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 C{'adjacent=False'} in the constructor.
+
+ Example::
+ real = Word(nums) + '.' + Word(nums)
+ print(real.parseString('3.1416')) # -> ['3', '.', '1416']
+ # will also erroneously match the following
+ print(real.parseString('3. 1416')) # -> ['3', '.', '1416']
+
+ real = Combine(Word(nums) + '.' + Word(nums))
+ print(real.parseString('3.1416')) # -> ['3.1416']
+ # no match when there are internal spaces
+ print(real.parseString('3. 1416')) # -> Exception: Expected W:(0123...)
"""
def __init__( self, expr, joinString="", adjacent=True ):
super(Combine,self).__init__( expr )
@@ -3072,7 +4221,19 @@ class Combine(TokenConverter): return retToks
class Group(TokenConverter):
- """Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions."""
+ """
+ Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.
+
+ Example::
+ ident = Word(alphas)
+ num = Word(nums)
+ term = ident | num
+ func = ident + Optional(delimitedList(term))
+ print(func.parseString("fn a,b,100")) # -> ['fn', 'a', 'b', '100']
+
+ func = ident + Group(Optional(delimitedList(term)))
+ print(func.parseString("fn a,b,100")) # -> ['fn', ['a', 'b', '100']]
+ """
def __init__( self, expr ):
super(Group,self).__init__( expr )
self.saveAsList = True
@@ -3081,9 +4242,40 @@ class Group(TokenConverter): 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.
+ """
+ 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.
+
+ Example::
+ data_word = Word(alphas)
+ label = data_word + FollowedBy(':')
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
+
+ text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
+ attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+
+ # print attributes as plain groups
+ print(OneOrMore(attr_expr).parseString(text).dump())
+
+ # instead of OneOrMore(expr), parse using Dict(OneOrMore(Group(expr))) - Dict will auto-assign names
+ result = Dict(OneOrMore(Group(attr_expr))).parseString(text)
+ print(result.dump())
+
+ # access named fields as dict entries, or output as dict
+ print(result['shape'])
+ print(result.asDict())
+ prints::
+ ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap']
+
+ [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
+ - color: light blue
+ - posn: upper left
+ - shape: SQUARE
+ - texture: burlap
+ SQUARE
+ {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'}
+ See more examples at L{ParseResults} of accessing fields by results name.
"""
def __init__( self, expr ):
super(Dict,self).__init__( expr )
@@ -3115,7 +4307,24 @@ class Dict(TokenConverter): class Suppress(TokenConverter):
- """Converter for ignoring the results of a parsed expression."""
+ """
+ Converter for ignoring the results of a parsed expression.
+
+ Example::
+ source = "a, b, c,d"
+ wd = Word(alphas)
+ wd_list1 = wd + ZeroOrMore(',' + wd)
+ print(wd_list1.parseString(source))
+
+ # often, delimiters that are useful during parsing are just in the
+ # way afterward - use Suppress to keep them out of the parsed output
+ wd_list2 = wd + ZeroOrMore(Suppress(',') + wd)
+ print(wd_list2.parseString(source))
+ prints::
+ ['a', ',', 'b', ',', 'c', ',', 'd']
+ ['a', 'b', 'c', 'd']
+ (See also L{delimitedList}.)
+ """
def postParse( self, instring, loc, tokenlist ):
return []
@@ -3124,7 +4333,9 @@ class Suppress(TokenConverter): class OnlyOnce(object):
- """Wrapper for parse actions, to ensure they are only called once."""
+ """
+ Wrapper for parse actions, to ensure they are only called once.
+ """
def __init__(self, methodCall):
self.callable = _trim_arity(methodCall)
self.called = False
@@ -3138,20 +4349,39 @@ class OnlyOnce(object): self.called = False
def traceParseAction(f):
- """Decorator for debugging parse actions."""
+ """
+ Decorator for debugging parse actions.
+
+ When the parse action is called, this decorator will print C{">> entering I{method-name}(line:I{current_source_line}, I{parse_location}, I{matched_tokens})".}
+ When the parse action completes, the decorator will print C{"<<"} followed by the returned value, or any exception that the parse action raised.
+
+ Example::
+ wd = Word(alphas)
+
+ @traceParseAction
+ def remove_duplicate_chars(tokens):
+ return ''.join(sorted(set(''.join(tokens)))
+
+ wds = OneOrMore(wd).setParseAction(remove_duplicate_chars)
+ print(wds.parseString("slkdjs sld sldd sdlf sdljf"))
+ prints::
+ >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {}))
+ <<leaving remove_duplicate_chars (ret: 'dfjkls')
+ ['dfjkls']
+ """
f = _trim_arity(f)
def z(*paArgs):
- thisFunc = f.func_name
+ thisFunc = f.__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) )
+ sys.stderr.write( ">>entering %s(line: '%s', %d, %r)\n" % (thisFunc,line(l,s),l,t) )
try:
ret = f(*paArgs)
except Exception as exc:
sys.stderr.write( "<<leaving %s (exception: %s)\n" % (thisFunc,exc) )
raise
- sys.stderr.write( "<<leaving %s (ret: %s)\n" % (thisFunc,ret) )
+ sys.stderr.write( "<<leaving %s (ret: %r)\n" % (thisFunc,ret) )
return ret
try:
z.__name__ = f.__name__
@@ -3163,12 +4393,17 @@ def traceParseAction(f): # global helpers
#
def delimitedList( expr, delim=",", combine=False ):
- """Helper to define a delimited list of expressions - the delimiter defaults to ','.
- By default, the list elements and delimiters can have intervening whitespace, and
- comments, but this can be overridden by passing C{combine=True} in the constructor.
- If C{combine} is set to C{True}, the matching tokens are returned as a single token
- string, with the delimiters included; otherwise, the matching tokens are returned
- as a list of tokens, with the delimiters suppressed.
+ """
+ Helper to define a delimited list of expressions - the delimiter defaults to ','.
+ By default, the list elements and delimiters can have intervening whitespace, and
+ comments, but this can be overridden by passing C{combine=True} in the constructor.
+ If C{combine} is set to C{True}, the matching tokens are returned as a single token
+ string, with the delimiters included; otherwise, the matching tokens are returned
+ as a list of tokens, with the delimiters suppressed.
+
+ Example::
+ delimitedList(Word(alphas)).parseString("aa,bb,cc") # -> ['aa', 'bb', 'cc']
+ delimitedList(Word(hexnums), delim=':', combine=True).parseString("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE']
"""
dlName = _ustr(expr)+" ["+_ustr(delim)+" "+_ustr(expr)+"]..."
if combine:
@@ -3177,11 +4412,22 @@ def delimitedList( expr, delim=",", combine=False ): return ( expr + ZeroOrMore( Suppress( delim ) + expr ) ).setName(dlName)
def countedArray( expr, intExpr=None ):
- """Helper to define a counted list of expressions.
- This helper defines a pattern of the form::
- integer expr expr expr...
- where the leading integer tells how many expr expressions follow.
- The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed.
+ """
+ Helper to define a counted list of expressions.
+ This helper defines a pattern of the form::
+ integer expr expr expr...
+ where the leading integer tells how many expr expressions follow.
+ The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed.
+
+ If C{intExpr} is specified, it should be a pyparsing expression that produces an integer value.
+
+ Example::
+ countedArray(Word(alphas)).parseString('2 ab cd ef') # -> ['ab', 'cd']
+
+ # in this parser, the leading integer value is given in binary,
+ # '10' indicating that 2 values are in the array
+ binaryConstant = Word('01').setParseAction(lambda t: int(t[0], 2))
+ countedArray(Word(alphas), intExpr=binaryConstant).parseString('10 ab cd ef') # -> ['ab', 'cd']
"""
arrayExpr = Forward()
def countFieldParseAction(s,l,t):
@@ -3194,7 +4440,7 @@ def countedArray( expr, intExpr=None ): intExpr = intExpr.copy()
intExpr.setName("arrayLen")
intExpr.addParseAction(countFieldParseAction, callDuringTry=True)
- return ( intExpr + arrayExpr )
+ return ( intExpr + arrayExpr ).setName('(len) ' + _ustr(expr) + '...')
def _flatten(L):
ret = []
@@ -3206,16 +4452,17 @@ def _flatten(L): return ret
def matchPreviousLiteral(expr):
- """Helper to define an expression that is indirectly defined from
- the tokens matched in a previous expression, that is, it looks
- for a 'repeat' of a previous expression. For example::
- first = Word(nums)
- second = matchPreviousLiteral(first)
- matchExpr = first + ":" + second
- will match C{"1:1"}, but not C{"1:2"}. Because this matches a
- previous literal, will also match the leading C{"1:1"} in C{"1:10"}.
- If this is not desired, use C{matchPreviousExpr}.
- Do *not* use with packrat parsing enabled.
+ """
+ Helper to define an expression that is indirectly defined from
+ the tokens matched in a previous expression, that is, it looks
+ for a 'repeat' of a previous expression. For example::
+ first = Word(nums)
+ second = matchPreviousLiteral(first)
+ matchExpr = first + ":" + second
+ will match C{"1:1"}, but not C{"1:2"}. Because this matches a
+ previous literal, will also match the leading C{"1:1"} in C{"1:10"}.
+ If this is not desired, use C{matchPreviousExpr}.
+ Do I{not} use with packrat parsing enabled.
"""
rep = Forward()
def copyTokenToRepeater(s,l,t):
@@ -3225,24 +4472,26 @@ def matchPreviousLiteral(expr): else:
# flatten t tokens
tflat = _flatten(t.asList())
- rep << And( [ Literal(tt) for tt in tflat ] )
+ rep << And(Literal(tt) for tt in tflat)
else:
rep << Empty()
expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
+ rep.setName('(prev) ' + _ustr(expr))
return rep
def matchPreviousExpr(expr):
- """Helper to define an expression that is indirectly defined from
- the tokens matched in a previous expression, that is, it looks
- for a 'repeat' of a previous expression. For example::
- first = Word(nums)
- second = matchPreviousExpr(first)
- matchExpr = first + ":" + second
- will match C{"1:1"}, but not C{"1:2"}. Because this matches by
- expressions, will *not* match the leading C{"1:1"} in C{"1:10"};
- the expressions are evaluated first, and then compared, so
- C{"1"} is compared with C{"10"}.
- Do *not* use with packrat parsing enabled.
+ """
+ Helper to define an expression that is indirectly defined from
+ the tokens matched in a previous expression, that is, it looks
+ for a 'repeat' of a previous expression. For example::
+ first = Word(nums)
+ second = matchPreviousExpr(first)
+ matchExpr = first + ":" + second
+ will match C{"1:1"}, but not C{"1:2"}. Because this matches by
+ expressions, will I{not} match the leading C{"1:1"} in C{"1:10"};
+ the expressions are evaluated first, and then compared, so
+ C{"1"} is compared with C{"10"}.
+ Do I{not} use with packrat parsing enabled.
"""
rep = Forward()
e2 = expr.copy()
@@ -3255,6 +4504,7 @@ def matchPreviousExpr(expr): raise ParseException("",0,"")
rep.setParseAction( mustMatchTheseTokens, callDuringTry=True )
expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
+ rep.setName('(prev) ' + _ustr(expr))
return rep
def _escapeRegexRangeChars(s):
@@ -3266,16 +4516,27 @@ def _escapeRegexRangeChars(s): return _ustr(s)
def oneOf( strs, caseless=False, useRegex=True ):
- """Helper to quickly define a set of alternative Literals, and makes sure to do
- longest-first testing when there is a conflict, regardless of the input order,
- but returns a C{L{MatchFirst}} for best performance.
-
- Parameters:
- - strs - a string of space-delimited literals, or a list of string literals
- - caseless - (default=False) - treat all literals as caseless
- - useRegex - (default=True) - as an optimization, will generate a Regex
+ """
+ Helper to quickly define a set of alternative Literals, and makes sure to do
+ longest-first testing when there is a conflict, regardless of the input order,
+ but returns a C{L{MatchFirst}} for best performance.
+
+ Parameters:
+ - strs - a string of space-delimited literals, or a collection of string literals
+ - caseless - (default=C{False}) - treat all literals as caseless
+ - useRegex - (default=C{True}) - as an optimization, will generate a Regex
object; otherwise, will generate a C{MatchFirst} object (if C{caseless=True}, or
if creating a C{Regex} raises an exception)
+
+ Example::
+ comp_oper = oneOf("< = > <= >= !=")
+ var = Word(alphas)
+ number = Word(nums)
+ term = var | number
+ comparison_expr = term + comp_oper + term
+ print(comparison_expr.searchString("B = 12 AA=23 B<=AA AA>12"))
+ prints::
+ [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']]
"""
if caseless:
isequal = ( lambda a,b: a.upper() == b.upper() )
@@ -3289,12 +4550,10 @@ def oneOf( strs, caseless=False, useRegex=True ): symbols = []
if isinstance(strs,basestring):
symbols = strs.split()
- elif isinstance(strs, collections.Sequence):
- symbols = list(strs[:])
- elif isinstance(strs, _generatorType):
+ elif isinstance(strs, collections.Iterable):
symbols = list(strs)
else:
- warnings.warn("Invalid argument to oneOf, expected string or list",
+ warnings.warn("Invalid argument to oneOf, expected string or iterable",
SyntaxWarning, stacklevel=2)
if not symbols:
return NoMatch()
@@ -3318,41 +4577,76 @@ def oneOf( strs, caseless=False, useRegex=True ): #~ print (strs,"->", "|".join( [ _escapeRegexChars(sym) for sym in symbols] ))
try:
if len(symbols)==len("".join(symbols)):
- return Regex( "[%s]" % "".join(_escapeRegexRangeChars(sym) for sym in symbols) )
+ return Regex( "[%s]" % "".join(_escapeRegexRangeChars(sym) for sym in symbols) ).setName(' | '.join(symbols))
else:
- return Regex( "|".join(re.escape(sym) for sym in symbols) )
+ return Regex( "|".join(re.escape(sym) for sym in symbols) ).setName(' | '.join(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 ] )
+ return MatchFirst(parseElementClass(sym) for sym in symbols).setName(' | '.join(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 C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{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 C{Dict} results can include named token
- fields.
+ """
+ Helper to easily and clearly define a dictionary by specifying the respective patterns
+ for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{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 C{Dict} results can include named token
+ fields.
+
+ Example::
+ text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
+ attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+ print(OneOrMore(attr_expr).parseString(text).dump())
+
+ attr_label = label
+ attr_value = Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join)
+
+ # similar to Dict, but simpler call format
+ result = dictOf(attr_label, attr_value).parseString(text)
+ print(result.dump())
+ print(result['shape'])
+ print(result.shape) # object attribute access works too
+ print(result.asDict())
+ prints::
+ [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
+ - color: light blue
+ - posn: upper left
+ - shape: SQUARE
+ - texture: burlap
+ SQUARE
+ SQUARE
+ {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'}
"""
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 C{L{keepOriginalText}}, and does not
- require the inspect module to chase up the call stack. By default, returns a
- string containing the original parsed text.
+ """
+ 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. By default, returns astring containing the original parsed text.
- If the optional C{asString} argument is passed as C{False}, then the return value is a
- C{L{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 C{L{originalTextFor}} contains expressions with defined
- results names, you must set C{asString} to C{False} if you want to preserve those
- results name values."""
+ If the optional C{asString} argument is passed as C{False}, then the return value is a
+ C{L{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 C{L{originalTextFor}} contains expressions with defined
+ results names, you must set C{asString} to C{False} if you want to preserve those
+ results name values.
+
+ Example::
+ src = "this is test <b> bold <i>text</i> </b> normal text "
+ for tag in ("b","i"):
+ opener,closer = makeHTMLTags(tag)
+ patt = originalTextFor(opener + SkipTo(closer) + closer)
+ print(patt.searchString(src)[0])
+ prints::
+ ['<b> bold <i>text</i> </b>']
+ ['<i>text</i>']
+ """
locMarker = Empty().setParseAction(lambda s,loc,t: loc)
endlocMarker = locMarker.copy()
endlocMarker.callPreparse = False
@@ -3361,27 +4655,37 @@ def originalTextFor(expr, asString=True): 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"]
+ t[:] = [s[t.pop('_original_start'):t.pop('_original_end')]]
matchExpr.setParseAction(extractText)
+ matchExpr.ignoreExprs = expr.ignoreExprs
return matchExpr
def ungroup(expr):
- """Helper to undo pyparsing's default grouping of And expressions, even
- if all but one are non-empty."""
+ """
+ Helper to undo pyparsing's default grouping of And expressions, even
+ if all but one are non-empty.
+ """
return TokenConverter(expr).setParseAction(lambda t:t[0])
def locatedExpr(expr):
- """Helper to decorate a returned token with its starting and ending locations in the input string.
- This helper adds the following results names:
- - locn_start = location where matched expression begins
- - locn_end = location where matched expression ends
- - value = the actual parsed results
-
- Be careful if the input text contains C{<TAB>} characters, you may want to call
- C{L{ParserElement.parseWithTabs}}
+ """
+ Helper to decorate a returned token with its starting and ending locations in the input string.
+ This helper adds the following results names:
+ - locn_start = location where matched expression begins
+ - locn_end = location where matched expression ends
+ - value = the actual parsed results
+
+ Be careful if the input text contains C{<TAB>} characters, you may want to call
+ C{L{ParserElement.parseWithTabs}}
+
+ Example::
+ wd = Word(alphas)
+ for match in locatedExpr(wd).searchString("ljsdf123lksdjjf123lkkjj1222"):
+ print(match)
+ prints::
+ [[0, 'ljsdf', 5]]
+ [[8, 'lksdjjf', 15]]
+ [[18, 'lkkjj', 23]]
"""
locator = Empty().setParseAction(lambda s,l,t: l)
return Group(locator("locn_start") + expr("value") + locator.copy().leaveWhitespace()("locn_end"))
@@ -3402,21 +4706,22 @@ _charRange = Group(_singleChar + Suppress("-") + _singleChar) _reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]"
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 '\x' (\x21, which is a '!' character)
- (\0x## is also supported for backwards compatibility)
- 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_$', etc.)
+ r"""
+ Helper to easily define string ranges for use in Word construction. Borrows
+ syntax from regexp '[]' string range definitions::
+ srange("[0-9]") -> "0123456789"
+ srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz"
+ srange("[a-z$_]") -> "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 C{\-} or C{\]})
+ - an escaped hex character with a leading C{'\x'} (C{\x21}, which is a C{'!'} character)
+ (C{\0x##} is also supported for backwards compatibility)
+ - an escaped octal character with a leading C{'\0'} (C{\041}, which is a C{'!'} character)
+ - a range of any of the above, separated by a dash (C{'a-z'}, etc.)
+ - any combination of the above (C{'aeiouy'}, C{'a-zA-Z0-9_$'}, etc.)
"""
_expanded = lambda p: p if not isinstance(p,ParseResults) else ''.join(unichr(c) for c in range(ord(p[0]),ord(p[1])+1))
try:
@@ -3425,8 +4730,9 @@ def srange(s): return ""
def matchOnlyAtCol(n):
- """Helper method for defining parse actions that require matching at a specific
- column in the input text.
+ """
+ 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:
@@ -3434,57 +4740,83 @@ def matchOnlyAtCol(n): return verifyCol
def replaceWith(replStr):
- """Helper method for common parse actions that simply return a literal value. Especially
- useful when used with C{L{transformString<ParserElement.transformString>}()}.
"""
- #def _replFunc(*args):
- # return [replStr]
- #return _replFunc
- return functools.partial(next, itertools.repeat([replStr]))
+ Helper method for common parse actions that simply return a literal value. Especially
+ useful when used with C{L{transformString<ParserElement.transformString>}()}.
+
+ Example::
+ num = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ na = oneOf("N/A NA").setParseAction(replaceWith(math.nan))
+ term = na | num
+
+ OneOrMore(term).parseString("324 234 N/A 234") # -> [324, 234, nan, 234]
+ """
+ return lambda s,l,t: [replStr]
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]
+ Helper parse action for removing quotation marks from parsed quoted strings.
-def upcaseTokens(s,l,t):
- """Helper parse action to convert tokens to upper case."""
- return [ tt.upper() for tt in map(_ustr,t) ]
+ Example::
+ # by default, quotation marks are included in parsed results
+ quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"]
-def downcaseTokens(s,l,t):
- """Helper parse action to convert tokens to lower case."""
- return [ tt.lower() for tt in map(_ustr,t) ]
+ # use removeQuotes to strip quotation marks from parsed results
+ quotedString.setParseAction(removeQuotes)
+ quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"]
+ """
+ return t[0][1:-1]
+
+def tokenMap(func, *args):
+ """
+ Helper to define a parse action by mapping a function to all elements of a ParseResults list.If any additional
+ args are passed, they are forwarded to the given function as additional arguments after
+ the token, as in C{hex_integer = Word(hexnums).setParseAction(tokenMap(int, 16))}, which will convert the
+ parsed data to an integer using base 16.
+
+ Example (compare the last to example in L{ParserElement.transformString}::
+ hex_ints = OneOrMore(Word(hexnums)).setParseAction(tokenMap(int, 16))
+ hex_ints.runTests('''
+ 00 11 22 aa FF 0a 0d 1a
+ ''')
+
+ upperword = Word(alphas).setParseAction(tokenMap(str.upper))
+ OneOrMore(upperword).runTests('''
+ my kingdom for a horse
+ ''')
+
+ wd = Word(alphas).setParseAction(tokenMap(str.title))
+ OneOrMore(wd).setParseAction(' '.join).runTests('''
+ now is the winter of our discontent made glorious summer by this sun of york
+ ''')
+ prints::
+ 00 11 22 aa FF 0a 0d 1a
+ [0, 17, 34, 170, 255, 10, 13, 26]
+
+ my kingdom for a horse
+ ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE']
+
+ now is the winter of our discontent made glorious summer by this sun of york
+ ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York']
+ """
+ def pa(s,l,t):
+ return [func(tokn, *args) for tokn in t]
-def keepOriginalText(s,startLoc,t):
- """DEPRECATED - use new helper method C{L{originalTextFor}}.
- 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
+ func_name = getattr(func, '__name__',
+ getattr(func, '__class__').__name__)
+ except Exception:
+ func_name = str(func)
+ pa.__name__ = func_name
+ return pa
+
+upcaseTokens = tokenMap(lambda t: _ustr(t).upper())
+"""(Deprecated) Helper parse action to convert tokens to upper case. Deprecated in favor of L{pyparsing_common.upcaseTokens}"""
+
+downcaseTokens = tokenMap(lambda t: _ustr(t).lower())
+"""(Deprecated) Helper parse action to convert tokens to lower case. Deprecated in favor of L{pyparsing_common.downcaseTokens}"""
+
def _makeTags(tagStr, xml):
"""Internal helper to construct opening and closing tag expressions, given a tag name"""
if isinstance(tagStr,basestring):
@@ -3508,40 +4840,90 @@ def _makeTags(tagStr, xml): Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
closeTag = Combine(_L("</") + tagStr + ">")
- openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % tagStr)
- closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("</%s>" % tagStr)
+ openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % resname)
+ closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("</%s>" % resname)
openTag.tag = resname
closeTag.tag = resname
return openTag, closeTag
def makeHTMLTags(tagStr):
- """Helper to construct opening and closing tag expressions for HTML, given a tag name"""
+ """
+ Helper to construct opening and closing tag expressions for HTML, given a tag name. Matches
+ tags in either upper or lower case, attributes with namespaces and with quoted or unquoted values.
+
+ Example::
+ text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
+ # makeHTMLTags returns pyparsing expressions for the opening and closing tags as a 2-tuple
+ a,a_end = makeHTMLTags("A")
+ link_expr = a + SkipTo(a_end)("link_text") + a_end
+
+ for link in link_expr.searchString(text):
+ # attributes in the <A> tag (like "href" shown here) are also accessible as named results
+ print(link.link_text, '->', link.href)
+ prints::
+ pyparsing -> http://pyparsing.wikispaces.com
+ """
return _makeTags( tagStr, False )
def makeXMLTags(tagStr):
- """Helper to construct opening and closing tag expressions for XML, given a tag name"""
+ """
+ Helper to construct opening and closing tag expressions for XML, given a tag name. Matches
+ tags only in the given upper/lower case.
+
+ Example: similar to L{makeHTMLTags}
+ """
return _makeTags( tagStr, True )
def withAttribute(*args,**attrDict):
- """Helper to create a validating parse action to be used with start tags created
- with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag
- with a required attribute value, to avoid false matches on common tags such as
- C{<TD>} or C{<DIV>}.
-
- Call C{withAttribute} with a series of attribute names and values. Specify the list
- of filter attributes names and values as:
- - keyword arguments, as in C{(align="right")}, or
- - as an explicit dict with C{**} operator, when an attribute name is also a Python
+ """
+ Helper to create a validating parse action to be used with start tags created
+ with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag
+ with a required attribute value, to avoid false matches on common tags such as
+ C{<TD>} or C{<DIV>}.
+
+ Call C{withAttribute} with a series of attribute names and values. Specify the list
+ of filter attributes names and values as:
+ - keyword arguments, as in C{(align="right")}, or
+ - as an explicit dict with C{**} operator, when an attribute name is also a Python
reserved word, as in C{**{"class":"Customer", "align":"right"}}
- - 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.
+ - 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.
- If just testing for C{class} (with or without a namespace), use C{L{withClass}}.
-
- To verify that the attribute exists, but without specifying a value, pass
- C{withAttribute.ANY_VALUE} as the value.
- """
+ If just testing for C{class} (with or without a namespace), use C{L{withClass}}.
+
+ To verify that the attribute exists, but without specifying a value, pass
+ C{withAttribute.ANY_VALUE} as the value.
+
+ Example::
+ html = '''
+ <div>
+ Some text
+ <div type="grid">1 4 0 1 0</div>
+ <div type="graph">1,3 2,3 1,1</div>
+ <div>this has no type</div>
+ </div>
+
+ '''
+ div,div_end = makeHTMLTags("div")
+
+ # only match div tag having a type attribute with value "grid"
+ div_grid = div().setParseAction(withAttribute(type="grid"))
+ grid_expr = div_grid + SkipTo(div | div_end)("body")
+ for grid_header in grid_expr.searchString(html):
+ print(grid_header.body)
+
+ # construct a match with any div tag having a type attribute, regardless of the value
+ div_any_type = div().setParseAction(withAttribute(type=withAttribute.ANY_VALUE))
+ div_expr = div_any_type + SkipTo(div | div_end)("body")
+ for div_header in div_expr.searchString(html):
+ print(div_header.body)
+ prints::
+ 1 4 0 1 0
+
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ """
if args:
attrs = args[:]
else:
@@ -3558,9 +4940,37 @@ def withAttribute(*args,**attrDict): withAttribute.ANY_VALUE = object()
def withClass(classname, namespace=''):
- """Simplified version of C{L{withAttribute}} when matching on a div class - made
- difficult because C{class} is a reserved word in Python.
- """
+ """
+ Simplified version of C{L{withAttribute}} when matching on a div class - made
+ difficult because C{class} is a reserved word in Python.
+
+ Example::
+ html = '''
+ <div>
+ Some text
+ <div class="grid">1 4 0 1 0</div>
+ <div class="graph">1,3 2,3 1,1</div>
+ <div>this <div> has no class</div>
+ </div>
+
+ '''
+ div,div_end = makeHTMLTags("div")
+ div_grid = div().setParseAction(withClass("grid"))
+
+ grid_expr = div_grid + SkipTo(div | div_end)("body")
+ for grid_header in grid_expr.searchString(html):
+ print(grid_header.body)
+
+ div_any_type = div().setParseAction(withClass(withAttribute.ANY_VALUE))
+ div_expr = div_any_type + SkipTo(div | div_end)("body")
+ for div_header in div_expr.searchString(html):
+ print(div_header.body)
+ prints::
+ 1 4 0 1 0
+
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ """
classattr = "%s:class" % namespace if namespace else "class"
return withAttribute(**{classattr : classname})
@@ -3569,40 +4979,69 @@ opAssoc.LEFT = object() opAssoc.RIGHT = object()
def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ):
- """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 C{opAssoc.RIGHT} and C{opAssoc.LEFT}.
- - parseAction is the parse action to be associated with
- expressions matching this operator expression (the
- parse action tuple member may be omitted)
- - lpar - expression for matching left-parentheses (default=Suppress('('))
- - rpar - expression for matching right-parentheses (default=Suppress(')'))
+ """
+ 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 C{opAssoc.RIGHT} and C{opAssoc.LEFT}.
+ - parseAction is the parse action to be associated with
+ expressions matching this operator expression (the
+ parse action tuple member may be omitted)
+ - lpar - expression for matching left-parentheses (default=C{Suppress('(')})
+ - rpar - expression for matching right-parentheses (default=C{Suppress(')')})
+
+ Example::
+ # simple example of four-function arithmetic with ints and variable names
+ integer = pyparsing_common.signed_integer
+ varname = pyparsing_common.identifier
+
+ arith_expr = infixNotation(integer | varname,
+ [
+ ('-', 1, opAssoc.RIGHT),
+ (oneOf('* /'), 2, opAssoc.LEFT),
+ (oneOf('+ -'), 2, opAssoc.LEFT),
+ ])
+
+ arith_expr.runTests('''
+ 5+3*6
+ (5+3)*6
+ -2--11
+ ''', fullDump=False)
+ prints::
+ 5+3*6
+ [[5, '+', [3, '*', 6]]]
+
+ (5+3)*6
+ [[[5, '+', 3], '*', 6]]
+
+ -2--11
+ [[['-', 2], '-', ['-', 11]]]
"""
ret = Forward()
lastExpr = baseExpr | ( lpar + ret + rpar )
for i,operDef in enumerate(opList):
opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4]
+ termName = "%s term" % opExpr if arity < 3 else "%s%s term" % opExpr
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)
+ thisExpr = Forward().setName(termName)
if rightLeftAssoc == opAssoc.LEFT:
if arity == 1:
matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) )
@@ -3636,37 +5075,77 @@ def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ): raise ValueError("operator must indicate right or left associativity")
if pa:
matchExpr.setParseAction( pa )
- thisExpr <<= ( matchExpr | lastExpr )
+ thisExpr <<= ( matchExpr.setName(termName) | lastExpr )
lastExpr = thisExpr
ret <<= lastExpr
return ret
+
operatorPrecedence = infixNotation
+"""(Deprecated) Former name of C{L{infixNotation}}, will be dropped in a future release."""
-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())
+dblQuotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"').setName("string enclosed in double quotes")
+sglQuotedString = Combine(Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("string enclosed in single quotes")
+quotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"'|
+ Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("quotedString using single or double quotes")
+unicodeString = Combine(_L('u') + quotedString.copy()).setName("unicode string literal")
def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()):
- """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 C{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 C{L{Or}} or C{L{MatchFirst}}.
- The default is L{quotedString}, but if no expressions are to be ignored,
- then pass C{None} for this argument.
+ """
+ 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=C{"("}); can also be a pyparsing expression
+ - closer - closing character for a nested list (default=C{")"}); can also be a pyparsing expression
+ - content - expression for items within the nested lists (default=C{None})
+ - ignoreExpr - expression for ignoring opening and closing delimiters (default=C{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 C{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 C{L{Or}} or C{L{MatchFirst}}.
+ The default is L{quotedString}, but if no expressions are to be ignored,
+ then pass C{None} for this argument.
+
+ Example::
+ data_type = oneOf("void int short long char float double")
+ decl_data_type = Combine(data_type + Optional(Word('*')))
+ ident = Word(alphas+'_', alphanums+'_')
+ number = pyparsing_common.number
+ arg = Group(decl_data_type + ident)
+ LPAR,RPAR = map(Suppress, "()")
+
+ code_body = nestedExpr('{', '}', ignoreExpr=(quotedString | cStyleComment))
+
+ c_function = (decl_data_type("type")
+ + ident("name")
+ + LPAR + Optional(delimitedList(arg), [])("args") + RPAR
+ + code_body("body"))
+ c_function.ignore(cStyleComment)
+
+ source_code = '''
+ int is_odd(int x) {
+ return (x%2);
+ }
+
+ int dec_to_hex(char hchar) {
+ if (hchar >= '0' && hchar <= '9') {
+ return (ord(hchar)-ord('0'));
+ } else {
+ return (10+ord(hchar)-ord('A'));
+ }
+ }
+ '''
+ for func in c_function.searchString(source_code):
+ print("%(name)s (%(type)s) args: %(args)s" % func)
+
+ prints::
+ is_odd (int) args: [['int', 'x']]
+ dec_to_hex (int) args: [['char', 'hchar']]
"""
if opener == closer:
raise ValueError("opening and closing strings cannot be the same")
@@ -3697,23 +5176,86 @@ def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.cop ret <<= Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) )
else:
ret <<= Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) )
+ ret.setName('nested %s%s expression' % (opener,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.
+ """
+ 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
+ Parameters:
+ - blockStatementExpr - expression defining syntax of statement that
is repeated within the indented block
- - indentStack - list created by caller to manage indentation stack
+ - 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
+ - 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 C{blockStatement}.
+ (default=C{True})
+
+ A valid block must contain at least one C{blockStatement}.
+
+ Example::
+ data = '''
+ def A(z):
+ A1
+ B = 100
+ G = A2
+ A2
+ A3
+ B
+ def BB(a,b,c):
+ BB1
+ def BBA():
+ bba1
+ bba2
+ bba3
+ C
+ D
+ def spam(x,y):
+ def eggs(z):
+ pass
+ '''
+
+
+ indentStack = [1]
+ stmt = Forward()
+
+ identifier = Word(alphas, alphanums)
+ funcDecl = ("def" + identifier + Group( "(" + Optional( delimitedList(identifier) ) + ")" ) + ":")
+ func_body = indentedBlock(stmt, indentStack)
+ funcDef = Group( funcDecl + func_body )
+
+ rvalue = Forward()
+ funcCall = Group(identifier + "(" + Optional(delimitedList(rvalue)) + ")")
+ rvalue << (funcCall | identifier | Word(nums))
+ assignment = Group(identifier + "=" + rvalue)
+ stmt << ( funcDef | assignment | identifier )
+
+ module_body = OneOrMore(stmt)
+
+ parseTree = module_body.parseString(data)
+ parseTree.pprint()
+ prints::
+ [['def',
+ 'A',
+ ['(', 'z', ')'],
+ ':',
+ [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]],
+ 'B',
+ ['def',
+ 'BB',
+ ['(', 'a', 'b', 'c', ')'],
+ ':',
+ [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]],
+ 'C',
+ 'D',
+ ['def',
+ 'spam',
+ ['(', 'x', 'y', ')'],
+ ':',
+ [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]]
"""
def checkPeerIndent(s,l,t):
if l >= len(s): return
@@ -3738,9 +5280,9 @@ def indentedBlock(blockStatementExpr, indentStack, indent=True): indentStack.pop()
NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress())
- INDENT = Empty() + Empty().setParseAction(checkSubIndent)
- PEER = Empty().setParseAction(checkPeerIndent)
- UNDENT = Empty().setParseAction(checkUnindent)
+ INDENT = (Empty() + Empty().setParseAction(checkSubIndent)).setName('INDENT')
+ PEER = Empty().setParseAction(checkPeerIndent).setName('')
+ UNDENT = Empty().setParseAction(checkUnindent).setName('UNINDENT')
if indent:
smExpr = Group( Optional(NL) +
#~ FollowedBy(blockStatementExpr) +
@@ -3749,57 +5291,387 @@ def indentedBlock(blockStatementExpr, indentStack, indent=True): smExpr = Group( Optional(NL) +
(OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) )
blockStatementExpr.ignore(_bslash + LineEnd())
- return smExpr
+ return smExpr.setName('indented block')
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
+anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:").setName('any tag'))
+_htmlEntityMap = dict(zip("gt lt amp nbsp quot apos".split(),'><& "\''))
+commonHTMLEntity = Regex('&(?P<entity>' + '|'.join(_htmlEntityMap.keys()) +");").setName("common HTML entity")
+def replaceHTMLEntity(t):
+ """Helper parser action to replace common HTML entities with their special characters"""
+ return _htmlEntityMap.get(t.entity)
# 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")
+cStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/').setName("C style comment")
+"Comment of the form C{/* ... */}"
+
+htmlComment = Regex(r"<!--[\s\S]*?-->").setName("HTML comment")
+"Comment of the form C{<!-- ... -->}"
+
+restOfLine = Regex(r".*").leaveWhitespace().setName("rest of line")
+dblSlashComment = Regex(r"//(?:\\\n|[^\n])*").setName("// comment")
+"Comment of the form C{// ... (to end of line)}"
-htmlComment = Regex(r"<!--[\s\S]*?-->")
-restOfLine = Regex(r".*").leaveWhitespace()
-dblSlashComment = Regex(r"\/\/(\\\n|.)*").setName("// comment")
-cppStyleComment = Regex(r"/(?:\*(?:[^*]*\*+)+?/|/[^\n]*(?:\n[^\n]*)*?(?:(?<!\\)|\Z))").setName("C++ style comment")
+cppStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/'| dblSlashComment).setName("C++ style comment")
+"Comment of either form C{L{cStyleComment}} or C{L{dblSlashComment}}"
javaStyleComment = cppStyleComment
+"Same as C{L{cppStyleComment}}"
+
pythonStyleComment = Regex(r"#.*").setName("Python style comment")
+"Comment of the form C{# ... (to end of line)}"
+
_commasepitem = Combine(OneOrMore(Word(printables, excludeChars=',') +
Optional( Word(" \t") +
~Literal(",") + ~LineEnd() ) ) ).streamline().setName("commaItem")
commaSeparatedList = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("commaSeparatedList")
+"""(Deprecated) Predefined expression of 1 or more printable words or quoted strings, separated by commas.
+ This expression is deprecated in favor of L{pyparsing_common.comma_separated_list}."""
+
+# some other useful expressions - using lower-case class name since we are really using this as a namespace
+class pyparsing_common:
+ """
+ Here are some common low-level expressions that may be useful in jump-starting parser development:
+ - numeric forms (L{integers<integer>}, L{reals<real>}, L{scientific notation<sci_real>})
+ - common L{programming identifiers<identifier>}
+ - network addresses (L{MAC<mac_address>}, L{IPv4<ipv4_address>}, L{IPv6<ipv6_address>})
+ - ISO8601 L{dates<iso8601_date>} and L{datetime<iso8601_datetime>}
+ - L{UUID<uuid>}
+ - L{comma-separated list<comma_separated_list>}
+ Parse actions:
+ - C{L{convertToInteger}}
+ - C{L{convertToFloat}}
+ - C{L{convertToDate}}
+ - C{L{convertToDatetime}}
+ - C{L{stripHTMLTags}}
+ - C{L{upcaseTokens}}
+ - C{L{downcaseTokens}}
+
+ Example::
+ pyparsing_common.number.runTests('''
+ # any int or real number, returned as the appropriate type
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ ''')
+
+ pyparsing_common.fnumber.runTests('''
+ # any int or real number, returned as float
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ ''')
+
+ pyparsing_common.hex_integer.runTests('''
+ # hex numbers
+ 100
+ FF
+ ''')
+
+ pyparsing_common.fraction.runTests('''
+ # fractions
+ 1/2
+ -3/4
+ ''')
+
+ pyparsing_common.mixed_integer.runTests('''
+ # mixed fractions
+ 1
+ 1/2
+ -3/4
+ 1-3/4
+ ''')
+
+ import uuid
+ pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
+ pyparsing_common.uuid.runTests('''
+ # uuid
+ 12345678-1234-5678-1234-567812345678
+ ''')
+ prints::
+ # any int or real number, returned as the appropriate type
+ 100
+ [100]
+
+ -100
+ [-100]
+
+ +100
+ [100]
+
+ 3.14159
+ [3.14159]
+
+ 6.02e23
+ [6.02e+23]
+
+ 1e-12
+ [1e-12]
+
+ # any int or real number, returned as float
+ 100
+ [100.0]
+
+ -100
+ [-100.0]
+
+ +100
+ [100.0]
+
+ 3.14159
+ [3.14159]
+
+ 6.02e23
+ [6.02e+23]
+
+ 1e-12
+ [1e-12]
+
+ # hex numbers
+ 100
+ [256]
+
+ FF
+ [255]
+
+ # fractions
+ 1/2
+ [0.5]
+
+ -3/4
+ [-0.75]
+
+ # mixed fractions
+ 1
+ [1]
+
+ 1/2
+ [0.5]
+
+ -3/4
+ [-0.75]
+
+ 1-3/4
+ [1.75]
+
+ # uuid
+ 12345678-1234-5678-1234-567812345678
+ [UUID('12345678-1234-5678-1234-567812345678')]
+ """
+
+ convertToInteger = tokenMap(int)
+ """
+ Parse action for converting parsed integers to Python int
+ """
+
+ convertToFloat = tokenMap(float)
+ """
+ Parse action for converting parsed numbers to Python float
+ """
+
+ integer = Word(nums).setName("integer").setParseAction(convertToInteger)
+ """expression that parses an unsigned integer, returns an int"""
+
+ hex_integer = Word(hexnums).setName("hex integer").setParseAction(tokenMap(int,16))
+ """expression that parses a hexadecimal integer, returns an int"""
+
+ signed_integer = Regex(r'[+-]?\d+').setName("signed integer").setParseAction(convertToInteger)
+ """expression that parses an integer with optional leading sign, returns an int"""
+
+ fraction = (signed_integer().setParseAction(convertToFloat) + '/' + signed_integer().setParseAction(convertToFloat)).setName("fraction")
+ """fractional expression of an integer divided by an integer, returns a float"""
+ fraction.addParseAction(lambda t: t[0]/t[-1])
+
+ mixed_integer = (fraction | signed_integer + Optional(Optional('-').suppress() + fraction)).setName("fraction or mixed integer-fraction")
+ """mixed integer of the form 'integer - fraction', with optional leading integer, returns float"""
+ mixed_integer.addParseAction(sum)
+
+ real = Regex(r'[+-]?\d+\.\d*').setName("real number").setParseAction(convertToFloat)
+ """expression that parses a floating point number and returns a float"""
+
+ sci_real = Regex(r'[+-]?\d+([eE][+-]?\d+|\.\d*([eE][+-]?\d+)?)').setName("real number with scientific notation").setParseAction(convertToFloat)
+ """expression that parses a floating point number with optional scientific notation and returns a float"""
+
+ # streamlining this expression makes the docs nicer-looking
+ number = (sci_real | real | signed_integer).streamline()
+ """any numeric expression, returns the corresponding Python type"""
+
+ fnumber = Regex(r'[+-]?\d+\.?\d*([eE][+-]?\d+)?').setName("fnumber").setParseAction(convertToFloat)
+ """any int or real number, returned as float"""
+
+ identifier = Word(alphas+'_', alphanums+'_').setName("identifier")
+ """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')"""
+
+ ipv4_address = Regex(r'(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}').setName("IPv4 address")
+ "IPv4 address (C{0.0.0.0 - 255.255.255.255})"
+
+ _ipv6_part = Regex(r'[0-9a-fA-F]{1,4}').setName("hex_integer")
+ _full_ipv6_address = (_ipv6_part + (':' + _ipv6_part)*7).setName("full IPv6 address")
+ _short_ipv6_address = (Optional(_ipv6_part + (':' + _ipv6_part)*(0,6)) + "::" + Optional(_ipv6_part + (':' + _ipv6_part)*(0,6))).setName("short IPv6 address")
+ _short_ipv6_address.addCondition(lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8)
+ _mixed_ipv6_address = ("::ffff:" + ipv4_address).setName("mixed IPv6 address")
+ ipv6_address = Combine((_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).setName("IPv6 address")).setName("IPv6 address")
+ "IPv6 address (long, short, or mixed form)"
+
+ mac_address = Regex(r'[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}').setName("MAC address")
+ "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)"
+
+ @staticmethod
+ def convertToDate(fmt="%Y-%m-%d"):
+ """
+ Helper to create a parse action for converting parsed date string to Python datetime.date
+
+ Params -
+ - fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%d"})
+
+ Example::
+ date_expr = pyparsing_common.iso8601_date.copy()
+ date_expr.setParseAction(pyparsing_common.convertToDate())
+ print(date_expr.parseString("1999-12-31"))
+ prints::
+ [datetime.date(1999, 12, 31)]
+ """
+ def cvt_fn(s,l,t):
+ try:
+ return datetime.strptime(t[0], fmt).date()
+ except ValueError as ve:
+ raise ParseException(s, l, str(ve))
+ return cvt_fn
+
+ @staticmethod
+ def convertToDatetime(fmt="%Y-%m-%dT%H:%M:%S.%f"):
+ """
+ Helper to create a parse action for converting parsed datetime string to Python datetime.datetime
+
+ Params -
+ - fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%dT%H:%M:%S.%f"})
+
+ Example::
+ dt_expr = pyparsing_common.iso8601_datetime.copy()
+ dt_expr.setParseAction(pyparsing_common.convertToDatetime())
+ print(dt_expr.parseString("1999-12-31T23:59:59.999"))
+ prints::
+ [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)]
+ """
+ def cvt_fn(s,l,t):
+ try:
+ return datetime.strptime(t[0], fmt)
+ except ValueError as ve:
+ raise ParseException(s, l, str(ve))
+ return cvt_fn
+
+ iso8601_date = Regex(r'(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?').setName("ISO8601 date")
+ "ISO8601 date (C{yyyy-mm-dd})"
+
+ iso8601_datetime = Regex(r'(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?').setName("ISO8601 datetime")
+ "ISO8601 datetime (C{yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)}) - trailing seconds, milliseconds, and timezone optional; accepts separating C{'T'} or C{' '}"
+
+ uuid = Regex(r'[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}').setName("UUID")
+ "UUID (C{xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx})"
+
+ _html_stripper = anyOpenTag.suppress() | anyCloseTag.suppress()
+ @staticmethod
+ def stripHTMLTags(s, l, tokens):
+ """
+ Parse action to remove HTML tags from web page HTML source
+
+ Example::
+ # strip HTML links from normal text
+ text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
+ td,td_end = makeHTMLTags("TD")
+ table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end
+
+ print(table_text.parseString(text).body) # -> 'More info at the pyparsing wiki page'
+ """
+ return pyparsing_common._html_stripper.transformString(tokens[0])
+
+ _commasepitem = Combine(OneOrMore(~Literal(",") + ~LineEnd() + Word(printables, excludeChars=',')
+ + Optional( White(" \t") ) ) ).streamline().setName("commaItem")
+ comma_separated_list = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("comma separated list")
+ """Predefined expression of 1 or more printable words or quoted strings, separated by commas."""
+
+ upcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).upper()))
+ """Parse action to convert tokens to upper case."""
+
+ downcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).lower()))
+ """Parse action to convert tokens to lower case."""
if __name__ == "__main__":
- 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" ) )
-
- simpleSQL.runTests("""\
- SELECT * from XYZZY, ABC
- select * from SYS.XYZZY
- Select A from Sys.dual
- Select AA,BB,CC from Sys.dual
- Select A, B, C from Sys.dual
- Select A, B, C from Sys.dual
- Xelect A, B, C from Sys.dual
- Select A, B, C frox Sys.dual
- Select
- Select ^^^ frox Sys.dual
- Select A, B, C from Sys.dual, Table2""")
+ selectToken = CaselessLiteral("select")
+ fromToken = CaselessLiteral("from")
+
+ ident = Word(alphas, alphanums + "_$")
+
+ columnName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
+ columnNameList = Group(delimitedList(columnName)).setName("columns")
+ columnSpec = ('*' | columnNameList)
+
+ tableName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
+ tableNameList = Group(delimitedList(tableName)).setName("tables")
+ simpleSQL = selectToken("command") + columnSpec("columns") + fromToken + tableNameList("tables")
+
+ # demo runTests method, including embedded comments in test string
+ simpleSQL.runTests("""
+ # '*' as column list and dotted table name
+ select * from SYS.XYZZY
+
+ # caseless match on "SELECT", and casts back to "select"
+ SELECT * from XYZZY, ABC
+
+ # list of column names, and mixed case SELECT keyword
+ Select AA,BB,CC from Sys.dual
+
+ # multiple tables
+ Select A, B, C from Sys.dual, Table2
+
+ # invalid SELECT keyword - should fail
+ Xelect A, B, C from Sys.dual
+
+ # incomplete command - should fail
+ Select
+
+ # invalid column name - should fail
+ Select ^^^ frox Sys.dual
+
+ """)
+
+ pyparsing_common.number.runTests("""
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ """)
+
+ # any int or real number, returned as float
+ pyparsing_common.fnumber.runTests("""
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ """)
+
+ pyparsing_common.hex_integer.runTests("""
+ 100
+ FF
+ """)
+
+ import uuid
+ pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
+ pyparsing_common.uuid.runTests("""
+ 12345678-1234-5678-1234-567812345678
+ """)
diff --git a/pkg_resources/_vendor/vendored.txt b/pkg_resources/_vendor/vendored.txt index 46532c0a..22e1309c 100644 --- a/pkg_resources/_vendor/vendored.txt +++ b/pkg_resources/_vendor/vendored.txt @@ -1,3 +1,4 @@ packaging==16.7 -pyparsing==2.0.6 +pyparsing==2.1.9 six==1.10.0 +appdirs==1.4.0 diff --git a/pkg_resources/extern/__init__.py b/pkg_resources/extern/__init__.py index 6758d36f..b4156fec 100644 --- a/pkg_resources/extern/__init__.py +++ b/pkg_resources/extern/__init__.py @@ -6,6 +6,7 @@ class VendorImporter: A PEP 302 meta path importer for finding optionally-vendored or otherwise naturally-installed packages from root_name. """ + def __init__(self, root_name, vendored_names=(), vendor_pkg=None): self.root_name = root_name self.vendored_names = set(vendored_names) @@ -67,5 +68,6 @@ class VendorImporter: if self not in sys.meta_path: sys.meta_path.append(self) -names = 'packaging', 'pyparsing', 'six' + +names = 'packaging', 'pyparsing', 'six', 'appdirs' VendorImporter(__name__, names).install() diff --git a/pkg_resources/tests/test_markers.py b/pkg_resources/tests/test_markers.py index 8d451de3..78810b6e 100644 --- a/pkg_resources/tests/test_markers.py +++ b/pkg_resources/tests/test_markers.py @@ -5,6 +5,7 @@ except ImportError: from pkg_resources import evaluate_marker + @mock.patch('platform.python_version', return_value='2.7.10') def test_ordering(python_version_mock): assert evaluate_marker("python_full_version > '2.7.3'") is True diff --git a/pkg_resources/tests/test_pkg_resources.py b/pkg_resources/tests/test_pkg_resources.py index 8b276ffc..361fe657 100644 --- a/pkg_resources/tests/test_pkg_resources.py +++ b/pkg_resources/tests/test_pkg_resources.py @@ -24,6 +24,7 @@ try: except NameError: unicode = str + def timestamp(dt): """ Return a timestamp for a local, naive datetime instance. @@ -34,13 +35,16 @@ def timestamp(dt): # Python 3.2 and earlier return time.mktime(dt.timetuple()) + class EggRemover(unicode): + def __call__(self): if self in sys.path: sys.path.remove(self) if os.path.exists(self): os.remove(self) + class TestZipProvider(object): finalizers = [] @@ -94,7 +98,9 @@ class TestZipProvider(object): assert f.read() == 'hello, world!' manager.cleanup_resources() + class TestResourceManager(object): + def test_get_cache_path(self): mgr = pkg_resources.ResourceManager() path = mgr.get_cache_path('foo') @@ -107,6 +113,7 @@ class TestIndependence: """ Tests to ensure that pkg_resources runs independently from setuptools. """ + def test_setuptools_not_imported(self): """ In a separate Python environment, import pkg_resources and assert @@ -122,7 +129,6 @@ class TestIndependence: subprocess.check_call(cmd) - class TestDeepVersionLookupDistutils(object): @pytest.fixture diff --git a/pkg_resources/tests/test_resources.py b/pkg_resources/tests/test_resources.py index 31847dc8..2ed56233 100644 --- a/pkg_resources/tests/test_resources.py +++ b/pkg_resources/tests/test_resources.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import os import sys import string +import platform from pkg_resources.extern.six.moves import map @@ -33,6 +34,7 @@ class Metadata(pkg_resources.EmptyProvider): dist_from_fn = pkg_resources.Distribution.from_filename + class TestDistro: def testCollection(self): @@ -50,15 +52,15 @@ class TestDistro: assert list(ad) == ['foopkg'] # Distributions sort by version - assert [dist.version for dist in ad['FooPkg']] == ['1.4','1.3-1','1.2'] + assert [dist.version for dist in ad['FooPkg']] == ['1.4', '1.3-1', '1.2'] # Removing a distribution leaves sequence alone ad.remove(ad['FooPkg'][1]) - assert [dist.version for dist in ad['FooPkg']] == ['1.4','1.2'] + assert [dist.version for dist in ad['FooPkg']] == ['1.4', '1.2'] # And inserting adds them in order ad.add(dist_from_fn("FooPkg-1.9.egg")) - assert [dist.version for dist in ad['FooPkg']] == ['1.9','1.4','1.2'] + assert [dist.version for dist in ad['FooPkg']] == ['1.9', '1.4', '1.2'] ws = WorkingSet([]) foo12 = dist_from_fn("FooPkg-1.2-py2.4.egg") @@ -85,7 +87,7 @@ class TestDistro: ws.add(foo14) assert ad.best_match(req, ws).version == '1.4' - def checkFooPkg(self,d): + def checkFooPkg(self, d): assert d.project_name == "FooPkg" assert d.key == "foopkg" assert d.version == "1.3.post1" @@ -96,13 +98,13 @@ class TestDistro: def testDistroBasics(self): d = Distribution( "/some/path", - project_name="FooPkg",version="1.3-1",py_version="2.4",platform="win32" + project_name="FooPkg", version="1.3-1", py_version="2.4", platform="win32" ) self.checkFooPkg(d) d = Distribution("/some/path") assert d.py_version == sys.version[:3] - assert d.platform == None + assert d.platform is None def testDistroParse(self): d = dist_from_fn("FooPkg-1.3.post1-py2.4-win32.egg") @@ -113,8 +115,8 @@ class TestDistro: def testDistroMetadata(self): d = Distribution( "/some/path", project_name="FooPkg", py_version="2.4", platform="win32", - metadata = Metadata( - ('PKG-INFO',"Metadata-Version: 1.0\nVersion: 1.3-1\n") + metadata=Metadata( + ('PKG-INFO', "Metadata-Version: 1.0\nVersion: 1.3-1\n") ) ) self.checkFooPkg(d) @@ -152,7 +154,7 @@ class TestDistro: list(map(ws.add, targets)) with pytest.raises(VersionConflict): ws.resolve(parse_requirements("Foo==0.9"), ad) - ws = WorkingSet([]) # reset + ws = WorkingSet([]) # reset # Request an extra that causes an unresolved dependency for "Baz" with pytest.raises(pkg_resources.DistributionNotFound): @@ -163,7 +165,7 @@ class TestDistro: ad.add(Baz) # Activation list now includes resolved dependency - assert list(ws.resolve(parse_requirements("Foo[bar]"), ad)) ==[Foo,Baz] + assert list(ws.resolve(parse_requirements("Foo[bar]"), ad)) == [Foo, Baz] # Requests for conflicting versions produce VersionConflict with pytest.raises(VersionConflict) as vc: ws.resolve(parse_requirements("Foo==1.2\nFoo!=1.2"), ad) @@ -217,7 +219,7 @@ class TestDistro: quux = Distribution.from_filename("/foo_dir/quux-1.0.dist-info") ad.add(quux) res = list(ws.resolve(parse_requirements("Foo[baz]"), ad)) - assert res == [Foo,quux] + assert res == [Foo, quux] def test_marker_evaluation_with_multiple_extras(self): ad = pkg_resources.Environment([]) @@ -237,7 +239,7 @@ class TestDistro: fred = Distribution.from_filename("/foo_dir/fred-0.1.dist-info") ad.add(fred) res = list(ws.resolve(parse_requirements("Foo[baz,bar]"), ad)) - assert sorted(res) == [fred,quux,Foo] + assert sorted(res) == [fred, quux, Foo] def test_marker_evaluation_with_extras_loop(self): ad = pkg_resources.Environment([]) @@ -273,19 +275,19 @@ class TestDistro: docutils>=0.3 [fastcgi] fcgiapp>=0.1""") - self.checkRequires(d,"Twisted>=1.5") + self.checkRequires(d, "Twisted>=1.5") self.checkRequires( - d,"Twisted>=1.5 ZConfig>=2.0 docutils>=0.3".split(), ["docgen"] + d, "Twisted>=1.5 ZConfig>=2.0 docutils>=0.3".split(), ["docgen"] ) self.checkRequires( - d,"Twisted>=1.5 fcgiapp>=0.1".split(), ["fastcgi"] + d, "Twisted>=1.5 fcgiapp>=0.1".split(), ["fastcgi"] ) self.checkRequires( - d,"Twisted>=1.5 ZConfig>=2.0 docutils>=0.3 fcgiapp>=0.1".split(), - ["docgen","fastcgi"] + d, "Twisted>=1.5 ZConfig>=2.0 docutils>=0.3 fcgiapp>=0.1".split(), + ["docgen", "fastcgi"] ) self.checkRequires( - d,"Twisted>=1.5 fcgiapp>=0.1 ZConfig>=2.0 docutils>=0.3".split(), + d, "Twisted>=1.5 fcgiapp>=0.1 ZConfig>=2.0 docutils>=0.3".split(), ["fastcgi", "docgen"] ) with pytest.raises(pkg_resources.UnknownExtra): @@ -293,6 +295,7 @@ class TestDistro: class TestWorkingSet: + def test_find_conflicting(self): ws = WorkingSet([]) Foo = Distribution.from_filename("/foo_dir/Foo-1.2.egg") @@ -347,7 +350,7 @@ class TestEntryPoints: def setup_method(self, method): self.dist = Distribution.from_filename( - "FooPkg-1.2-py2.4.egg", metadata=Metadata(('requires.txt','[x]'))) + "FooPkg-1.2-py2.4.egg", metadata=Metadata(('requires.txt', '[x]'))) def testBasics(self): ep = EntryPoint( @@ -379,6 +382,7 @@ class TestEntryPoints: assert ep.name == 'html+mako' reject_specs = "foo", "x=a:b:c", "q=x/na", "fez=pish:tush-z", "x=f[a]>2" + @pytest.mark.parametrize("reject_spec", reject_specs) def test_reject_spec(self, reject_spec): with pytest.raises(ValueError): @@ -404,7 +408,7 @@ class TestEntryPoints: submap_expect = dict( feature1=EntryPoint('feature1', 'somemodule', ['somefunction']), - feature2=EntryPoint('feature2', 'another.module', ['SomeClass'], ['extra1','extra2']), + feature2=EntryPoint('feature2', 'another.module', ['SomeClass'], ['extra1', 'extra2']), feature3=EntryPoint('feature3', 'this.module', extras=['something']) ) submap_str = """ @@ -422,10 +426,10 @@ class TestEntryPoints: EntryPoint.parse_group("x", ["foo=baz", "foo=bar"]) def testParseMap(self): - m = EntryPoint.parse_map({'xyz':self.submap_str}) + m = EntryPoint.parse_map({'xyz': self.submap_str}) self.checkSubMap(m['xyz']) assert list(m.keys()) == ['xyz'] - m = EntryPoint.parse_map("[xyz]\n"+self.submap_str) + m = EntryPoint.parse_map("[xyz]\n" + self.submap_str) self.checkSubMap(m['xyz']) assert list(m.keys()) == ['xyz'] with pytest.raises(ValueError): @@ -433,6 +437,7 @@ class TestEntryPoints: with pytest.raises(ValueError): EntryPoint.parse_map(self.submap_str) + class TestRequirements: def testBasics(self): @@ -479,7 +484,7 @@ class TestRequirements: hash(( "twisted", packaging.specifiers.SpecifierSet(">=1.2"), - frozenset(["foo","bar"]), + frozenset(["foo", "bar"]), None )) ) @@ -520,9 +525,9 @@ class TestParsing: assert list(parse_requirements('')) == [] def testYielding(self): - for inp,out in [ - ([], []), ('x',['x']), ([[]],[]), (' x\n y', ['x','y']), - (['x\n\n','y'], ['x','y']), + for inp, out in [ + ([], []), ('x', ['x']), ([[]], []), (' x\n y', ['x', 'y']), + (['x\n\n', 'y'], ['x', 'y']), ]: assert list(pkg_resources.yield_lines(inp)) == out @@ -625,9 +630,9 @@ class TestParsing: req, = parse_requirements('foo >= 1.0, < 3') def testVersionEquality(self): - def c(s1,s2): - p1, p2 = parse_version(s1),parse_version(s2) - assert p1 == p2, (s1,s2,p1,p2) + def c(s1, s2): + p1, p2 = parse_version(s1), parse_version(s2) + assert p1 == p2, (s1, s2, p1, p2) c('1.2-rc1', '1.2rc1') c('0.4', '0.4.0') @@ -641,13 +646,13 @@ class TestParsing: c('1.2.a', '1.2a') def testVersionOrdering(self): - def c(s1,s2): - p1, p2 = parse_version(s1),parse_version(s2) - assert p1<p2, (s1,s2,p1,p2) + def c(s1, s2): + p1, p2 = parse_version(s1), parse_version(s2) + assert p1 < p2, (s1, s2, p1, p2) - c('2.1','2.1.1') - c('2a1','2b0') - c('2a1','2.1') + c('2.1', '2.1.1') + c('2a1', '2b0') + c('2a1', '2.1') c('2.3a1', '2.3') c('2.1-1', '2.1-2') c('2.1-1', '2.1.1') @@ -659,18 +664,18 @@ class TestParsing: c('0.4', '4.0') c('0.0.4', '0.4.0') c('0post1', '0.4post1') - c('2.1.0-rc1','2.1.0') - c('2.1dev','2.1a0') + c('2.1.0-rc1', '2.1.0') + c('2.1dev', '2.1a0') - torture =""" + torture = """ 0.80.1-3 0.80.1-2 0.80.1-1 0.79.9999+0.80.0pre4-1 0.79.9999+0.80.0pre2-3 0.79.9999+0.80.0pre2-2 0.77.2-1 0.77.1-1 0.77.0-1 """.split() - for p,v1 in enumerate(torture): - for v2 in torture[p+1:]: - c(v2,v1) + for p, v1 in enumerate(torture): + for v2 in torture[p + 1:]: + c(v2, v1) def testVersionBuildout(self): """ @@ -763,6 +768,9 @@ class TestNamespaces: pkg_resources._namespace_packages = saved_ns_pkgs sys.path = saved_sys_path + issue591 = pytest.mark.xfail(platform.system() == 'Windows', reason="#591") + + @issue591 def test_two_levels_deep(self, symlinked_tmpdir): """ Test nested namespace packages @@ -796,6 +804,7 @@ class TestNamespaces: ] assert pkg1.pkg2.__path__ == expected + @issue591 def test_path_order(self, symlinked_tmpdir): """ Test that if multiple versions of the same namespace package subpackage |