From dfb184c1a41c8294048db88dd8c8b378aaaee561 Mon Sep 17 00:00:00 2001 From: Daniel Rojas Date: Sun, 28 Jun 2020 10:39:11 +0200 Subject: [PATCH 01/12] Move source from src/ to src/wireviz/ in preparation for merge of refactor brancb --- src/{ => wireviz}/.gitignore | 0 src/{ => wireviz}/batch.py | 0 src/{ => wireviz}/wireviz.py | 0 src/{ => wireviz}/wv_colors.py | 0 src/{ => wireviz}/wv_helper.py | 0 5 files changed, 0 insertions(+), 0 deletions(-) rename src/{ => wireviz}/.gitignore (100%) rename src/{ => wireviz}/batch.py (100%) rename src/{ => wireviz}/wireviz.py (100%) rename src/{ => wireviz}/wv_colors.py (100%) rename src/{ => wireviz}/wv_helper.py (100%) diff --git a/src/.gitignore b/src/wireviz/.gitignore similarity index 100% rename from src/.gitignore rename to src/wireviz/.gitignore diff --git a/src/batch.py b/src/wireviz/batch.py similarity index 100% rename from src/batch.py rename to src/wireviz/batch.py diff --git a/src/wireviz.py b/src/wireviz/wireviz.py similarity index 100% rename from src/wireviz.py rename to src/wireviz/wireviz.py diff --git a/src/wv_colors.py b/src/wireviz/wv_colors.py similarity index 100% rename from src/wv_colors.py rename to src/wireviz/wv_colors.py diff --git a/src/wv_helper.py b/src/wireviz/wv_helper.py similarity index 100% rename from src/wv_helper.py rename to src/wireviz/wv_helper.py From 5514fd424420e170986e225b27ebcbde20fc06eb Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Wed, 24 Jun 2020 18:59:42 +0200 Subject: [PATCH 02/12] refactor dependencies and installation There are hard copies of the graphviz and pyyaml dependencies included in the repo. Remove these. Sort out installation and dependency handling by writing a functional setup.py script. Rename top level documentation. Refactor wireviz.py slightly to allow it to run as an installed script. # Conflicts: # src/batch.py # src/wireviz/batch.py # src/wireviz/build_examples.py --- .gitignore | 9 +- LICENSE.txt => LICENSE | 0 readme.md => README.md | 2 +- todo.md => TODO | 0 requirements.txt | 1 + setup.py | 45 ++ src/graphviz/__init__.py | 63 -- src/graphviz/_compat.py | 69 -- src/graphviz/backend.py | 312 ------- src/graphviz/dot.py | 287 ------- src/graphviz/files.py | 311 ------- src/graphviz/lang.py | 195 ----- src/graphviz/tools.py | 47 -- src/wireviz/__init__.py | 0 src/wireviz/build_examples.py | 54 ++ src/wireviz/wireviz.py | 12 +- src/yaml/__init__.py | 427 ---------- src/yaml/composer.py | 139 ---- src/yaml/constructor.py | 748 ----------------- src/yaml/cyaml.py | 101 --- src/yaml/dumper.py | 62 -- src/yaml/emitter.py | 1137 -------------------------- src/yaml/error.py | 75 -- src/yaml/events.py | 86 -- src/yaml/loader.py | 63 -- src/yaml/nodes.py | 49 -- src/yaml/parser.py | 589 -------------- src/yaml/reader.py | 185 ----- src/yaml/representer.py | 389 --------- src/yaml/resolver.py | 227 ------ src/yaml/scanner.py | 1435 --------------------------------- src/yaml/serializer.py | 111 --- src/yaml/tokens.py | 104 --- 33 files changed, 117 insertions(+), 7217 deletions(-) rename LICENSE.txt => LICENSE (100%) rename readme.md => README.md (95%) rename todo.md => TODO (100%) create mode 100644 requirements.txt create mode 100644 setup.py delete mode 100644 src/graphviz/__init__.py delete mode 100644 src/graphviz/_compat.py delete mode 100644 src/graphviz/backend.py delete mode 100644 src/graphviz/dot.py delete mode 100644 src/graphviz/files.py delete mode 100644 src/graphviz/lang.py delete mode 100644 src/graphviz/tools.py create mode 100644 src/wireviz/__init__.py create mode 100644 src/wireviz/build_examples.py delete mode 100644 src/yaml/__init__.py delete mode 100644 src/yaml/composer.py delete mode 100644 src/yaml/constructor.py delete mode 100644 src/yaml/cyaml.py delete mode 100644 src/yaml/dumper.py delete mode 100644 src/yaml/emitter.py delete mode 100644 src/yaml/error.py delete mode 100644 src/yaml/events.py delete mode 100644 src/yaml/loader.py delete mode 100644 src/yaml/nodes.py delete mode 100644 src/yaml/parser.py delete mode 100644 src/yaml/reader.py delete mode 100644 src/yaml/representer.py delete mode 100644 src/yaml/resolver.py delete mode 100644 src/yaml/scanner.py delete mode 100644 src/yaml/serializer.py delete mode 100644 src/yaml/tokens.py diff --git a/.gitignore b/.gitignore index 79b2f55..c121d2f 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,9 @@ .DS_Store -temp/ +.eggs +__pycache__ +.*.swp +*.egg-info +*.pyc +build +data +dist diff --git a/LICENSE.txt b/LICENSE similarity index 100% rename from LICENSE.txt rename to LICENSE diff --git a/readme.md b/README.md similarity index 95% rename from readme.md rename to README.md index bca9684..df7092a 100644 --- a/readme.md +++ b/README.md @@ -94,7 +94,7 @@ mywire.html HTML page with wiring diagram and BOM embedded ## Status -This is very much a [work in progress](todo.md). Source code, API, syntax and functionality may change wildly at any time. +This is very much a [work in progress](TODO). Source code, API, syntax and functionality may change wildly at any time. ## Requirements diff --git a/todo.md b/TODO similarity index 100% rename from todo.md rename to TODO diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..9c558e3 --- /dev/null +++ b/requirements.txt @@ -0,0 +1 @@ +. diff --git a/setup.py b/setup.py new file mode 100644 index 0000000..83dbc55 --- /dev/null +++ b/setup.py @@ -0,0 +1,45 @@ +#!/usr/bin/python3 + +import os +from setuptools import setup, find_packages + +project_name = 'wireviz' + +# Utility function to read the README file. +# Used for the long_description. It's nice, because now 1) we have a top level +# README file and 2) it's easier to type in the README file than to put a raw +# string in below ... +def read(fname): + return open(os.path.join(os.path.dirname(__file__), fname)).read() + +setup( + name=project_name, + version='0.1', + author='Daniel Rojas', + #author_email='', + description='Easily document cables and wiring harnesses', + long_description=read(os.path.join(os.path.dirname(__file__), 'README.md')), + long_description_content_type='text/markdown', + install_requires=[ + 'pyyaml', + 'graphviz', + ], + license='GPLv3', + keywords='cable connector hardware harness wiring wiring-diagram wiring-harness', + url='https://github.com/n42/WireViz', + package_dir={'': 'src'}, + packages=find_packages('src'), + entry_points={ + 'console_scripts': ['wireviz=wireviz.wireviz:main'], + }, + classifiers=[ + 'Development Status :: 4 - Beta', + 'Environment :: Console', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.7', + 'Programming Language :: Python :: 3.8', + 'Topic :: Utilities', + 'License :: OSI Approved :: GNU General Public License v3 (GPLv3)', + ], + +) diff --git a/src/graphviz/__init__.py b/src/graphviz/__init__.py deleted file mode 100644 index 66760eb..0000000 --- a/src/graphviz/__init__.py +++ /dev/null @@ -1,63 +0,0 @@ -# graphviz - create dot, save, render, view - -"""Assemble DOT source code and render it with Graphviz. - ->>> dot = Digraph(comment='The Round Table') - ->>> dot.node('A', 'King Arthur') ->>> dot.node('B', 'Sir Bedevere the Wise') ->>> dot.node('L', 'Sir Lancelot the Brave') - ->>> dot.edges(['AB', 'AL']) - ->>> dot.edge('B', 'L', constraint='false') - ->>> print(dot) #doctest: +NORMALIZE_WHITESPACE -// The Round Table -digraph { - A [label="King Arthur"] - B [label="Sir Bedevere the Wise"] - L [label="Sir Lancelot the Brave"] - A -> B - A -> L - B -> L [constraint=false] -} -""" - -from .dot import Graph, Digraph -from .files import Source -from .lang import escape, nohtml -from .backend import (render, pipe, version, view, - ENGINES, FORMATS, RENDERERS, FORMATTERS, - ExecutableNotFound, RequiredArgumentError) - -__all__ = [ - 'Graph', 'Digraph', - 'Source', - 'escape', 'nohtml', - 'render', 'pipe', 'version', 'view', - 'ENGINES', 'FORMATS', 'RENDERERS', 'FORMATTERS', - 'ExecutableNotFound', 'RequiredArgumentError', -] - -__title__ = 'graphviz' -__version__ = '0.14.1.dev0' -__author__ = 'Sebastian Bank ' -__license__ = 'MIT, see LICENSE.txt' -__copyright__ = 'Copyright (c) 2013-2020 Sebastian Bank' - -#: Set of known layout commands used for rendering (``'dot'``, ``'neato'``, ...) -ENGINES = ENGINES - -#: Set of known output formats for rendering (``'pdf'``, ``'png'``, ...) -FORMATS = FORMATS - -#: Set of known output formatters for rendering (``'cairo'``, ``'gd'``, ...) -FORMATTERS = FORMATTERS - -#: Set of known output renderers for rendering (``'cairo'``, ``'gd'``, ...) -RENDERERS = RENDERERS - -ExecutableNotFound = ExecutableNotFound - -RequiredArgumentError = RequiredArgumentError diff --git a/src/graphviz/_compat.py b/src/graphviz/_compat.py deleted file mode 100644 index 7d6fc7b..0000000 --- a/src/graphviz/_compat.py +++ /dev/null @@ -1,69 +0,0 @@ -# _compat.py - Python 2/3 compatibility - -import os -import sys -import operator -import subprocess - -PY2 = (sys.version_info.major == 2) - - -if PY2: - string_classes = (str, unicode) # needed individually for sublassing - text_type = unicode - - iteritems = operator.methodcaller('iteritems') - - def makedirs(name, mode=0o777, exist_ok=False): - try: - os.makedirs(name, mode) - except OSError: - if not exist_ok or not os.path.isdir(name): - raise - - def stderr_write_bytes(data, flush=False): - """Write data str to sys.stderr (flush if requested).""" - sys.stderr.write(data) - if flush: - sys.stderr.flush() - - def Popen_stderr_devnull(*args, **kwargs): # noqa: N802 - with open(os.devnull, 'w') as f: - return subprocess.Popen(*args, stderr=f, **kwargs) - - class CalledProcessError(subprocess.CalledProcessError): - - def __init__(self, returncode, cmd, output=None, stderr=None): - super(CalledProcessError, self).__init__(returncode, cmd, output) - self.stderr = stderr - - @property # pragma: no cover - def stdout(self): - return self.output - - @stdout.setter # pragma: no cover - def stdout(self, value): - self.output = value - - -else: - string_classes = (str,) - text_type = str - - def iteritems(d): - return iter(d.items()) - - def makedirs(name, mode=0o777, exist_ok=False): # allow os.makedirs mocking - return os.makedirs(name, mode, exist_ok=exist_ok) - - def stderr_write_bytes(data, flush=False): - """Encode data str and write to sys.stderr (flush if requested).""" - encoding = sys.stderr.encoding or sys.getdefaultencoding() - sys.stderr.write(data.decode(encoding)) - if flush: - sys.stderr.flush() - - def Popen_stderr_devnull(*args, **kwargs): # noqa: N802 - return subprocess.Popen(*args, stderr=subprocess.DEVNULL, **kwargs) - - CalledProcessError = subprocess.CalledProcessError diff --git a/src/graphviz/backend.py b/src/graphviz/backend.py deleted file mode 100644 index 6f4cc0c..0000000 --- a/src/graphviz/backend.py +++ /dev/null @@ -1,312 +0,0 @@ -# backend.py - execute rendering, open files in viewer - -import os -import re -import errno -import logging -import platform -import subprocess - -from . import _compat - -from . import tools - -__all__ = [ - 'render', 'pipe', 'version', 'view', - 'ENGINES', 'FORMATS', 'RENDERERS', 'FORMATTERS', - 'ExecutableNotFound', 'RequiredArgumentError', -] - -ENGINES = { # http://www.graphviz.org/pdf/dot.1.pdf - 'dot', 'neato', 'twopi', 'circo', 'fdp', 'sfdp', 'patchwork', 'osage', -} - -FORMATS = { # http://www.graphviz.org/doc/info/output.html - 'bmp', - 'canon', 'dot', 'gv', 'xdot', 'xdot1.2', 'xdot1.4', - 'cgimage', - 'cmap', - 'eps', - 'exr', - 'fig', - 'gd', 'gd2', - 'gif', - 'gtk', - 'ico', - 'imap', 'cmapx', - 'imap_np', 'cmapx_np', - 'ismap', - 'jp2', - 'jpg', 'jpeg', 'jpe', - 'json', 'json0', 'dot_json', 'xdot_json', # Graphviz 2.40 - 'pct', 'pict', - 'pdf', - 'pic', - 'plain', 'plain-ext', - 'png', - 'pov', - 'ps', - 'ps2', - 'psd', - 'sgi', - 'svg', 'svgz', - 'tga', - 'tif', 'tiff', - 'tk', - 'vml', 'vmlz', - 'vrml', - 'wbmp', - 'webp', - 'xlib', - 'x11', -} - -RENDERERS = { # $ dot -T: - 'cairo', - 'dot', - 'fig', - 'gd', - 'gdiplus', - 'map', - 'pic', - 'pov', - 'ps', - 'svg', - 'tk', - 'vml', - 'vrml', - 'xdot', -} - -FORMATTERS = {'cairo', 'core', 'gd', 'gdiplus', 'gdwbmp', 'xlib'} - -PLATFORM = platform.system().lower() - - -log = logging.getLogger(__name__) - - -class ExecutableNotFound(RuntimeError): - """Exception raised if the Graphviz executable is not found.""" - - _msg = ('failed to execute %r, ' - 'make sure the Graphviz executables are on your systems\' PATH') - - def __init__(self, args): - super(ExecutableNotFound, self).__init__(self._msg % args) - - -class RequiredArgumentError(Exception): - """Exception raised if a required argument is missing.""" - - -class CalledProcessError(_compat.CalledProcessError): - - def __str__(self): - s = super(CalledProcessError, self).__str__() - return '%s [stderr: %r]' % (s, self.stderr) - - -def command(engine, format_, filepath=None, renderer=None, formatter=None): - """Return args list for ``subprocess.Popen`` and name of the rendered file.""" - if formatter is not None and renderer is None: - raise RequiredArgumentError('formatter given without renderer') - - if engine not in ENGINES: - raise ValueError('unknown engine: %r' % engine) - if format_ not in FORMATS: - raise ValueError('unknown format: %r' % format_) - if renderer is not None and renderer not in RENDERERS: - raise ValueError('unknown renderer: %r' % renderer) - if formatter is not None and formatter not in FORMATTERS: - raise ValueError('unknown formatter: %r' % formatter) - - output_format = [f for f in (format_, renderer, formatter) if f is not None] - cmd = [engine, '-T%s' % ':'.join(output_format)] - - if filepath is None: - rendered = None - else: - cmd.extend(['-O', filepath]) - suffix = '.'.join(reversed(output_format)) - rendered = '%s.%s' % (filepath, suffix) - - return cmd, rendered - - -if PLATFORM == 'windows': # pragma: no cover - def get_startupinfo(): - """Return subprocess.STARTUPINFO instance hiding the console window.""" - startupinfo = subprocess.STARTUPINFO() - startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW - startupinfo.wShowWindow = subprocess.SW_HIDE - return startupinfo -else: - def get_startupinfo(): - """Return None for startupinfo argument of ``subprocess.Popen``.""" - return None - - -def run(cmd, input=None, capture_output=False, check=False, encoding=None, - quiet=False, **kwargs): - """Run the command described by cmd and return its (stdout, stderr) tuple.""" - log.debug('run %r', cmd) - - if input is not None: - kwargs['stdin'] = subprocess.PIPE - if encoding is not None: - input = input.encode(encoding) - - if capture_output: - kwargs['stdout'] = kwargs['stderr'] = subprocess.PIPE - - try: - proc = subprocess.Popen(cmd, startupinfo=get_startupinfo(), **kwargs) - except OSError as e: - if e.errno == errno.ENOENT: - raise ExecutableNotFound(cmd) - else: - raise - - out, err = proc.communicate(input) - - if not quiet and err: - _compat.stderr_write_bytes(err, flush=True) - - if encoding is not None: - if out is not None: - out = out.decode(encoding) - if err is not None: - err = err.decode(encoding) - - if check and proc.returncode: - raise CalledProcessError(proc.returncode, cmd, - output=out, stderr=err) - - return out, err - - -def render(engine, format, filepath, renderer=None, formatter=None, quiet=False): - """Render file with Graphviz ``engine`` into ``format``, return result filename. - - Args: - engine: The layout commmand used for rendering (``'dot'``, ``'neato'``, ...). - format: The output format used for rendering (``'pdf'``, ``'png'``, ...). - filepath: Path to the DOT source file to render. - renderer: The output renderer used for rendering (``'cairo'``, ``'gd'``, ...). - formatter: The output formatter used for rendering (``'cairo'``, ``'gd'``, ...). - quiet (bool): Suppress ``stderr`` output from the layout subprocess. - Returns: - The (possibly relative) path of the rendered file. - Raises: - ValueError: If ``engine``, ``format``, ``renderer``, or ``formatter`` are not known. - graphviz.RequiredArgumentError: If ``formatter`` is given but ``renderer`` is None. - graphviz.ExecutableNotFound: If the Graphviz executable is not found. - subprocess.CalledProcessError: If the exit status is non-zero. - - The layout command is started from the directory of ``filepath``, so that - references to external files (e.g. ``[image=...]``) can be given as paths - relative to the DOT source file. - """ - dirname, filename = os.path.split(filepath) - del filepath - - cmd, rendered = command(engine, format, filename, renderer, formatter) - if dirname: - cwd = dirname - rendered = os.path.join(dirname, rendered) - else: - cwd = None - - run(cmd, capture_output=True, cwd=cwd, check=True, quiet=quiet) - return rendered - - -def pipe(engine, format, data, renderer=None, formatter=None, quiet=False): - """Return ``data`` piped through Graphviz ``engine`` into ``format``. - - Args: - engine: The layout commmand used for rendering (``'dot'``, ``'neato'``, ...). - format: The output format used for rendering (``'pdf'``, ``'png'``, ...). - data: The binary (encoded) DOT source string to render. - renderer: The output renderer used for rendering (``'cairo'``, ``'gd'``, ...). - formatter: The output formatter used for rendering (``'cairo'``, ``'gd'``, ...). - quiet (bool): Suppress ``stderr`` output from the layout subprocess. - Returns: - Binary (encoded) stdout of the layout command. - Raises: - ValueError: If ``engine``, ``format``, ``renderer``, or ``formatter`` are not known. - graphviz.RequiredArgumentError: If ``formatter`` is given but ``renderer`` is None. - graphviz.ExecutableNotFound: If the Graphviz executable is not found. - subprocess.CalledProcessError: If the exit status is non-zero. - """ - cmd, _ = command(engine, format, None, renderer, formatter) - out, _ = run(cmd, input=data, capture_output=True, check=True, quiet=quiet) - return out - - -def version(): - """Return the version number tuple from the ``stderr`` output of ``dot -V``. - - Returns: - Two, three, or four ``int`` version ``tuple``. - Raises: - graphviz.ExecutableNotFound: If the Graphviz executable is not found. - subprocess.CalledProcessError: If the exit status is non-zero. - RuntimmeError: If the output cannot be parsed into a version number. - """ - cmd = ['dot', '-V'] - out, _ = run(cmd, check=True, encoding='ascii', - stdout=subprocess.PIPE, - stderr=subprocess.STDOUT) - - ma = re.search(r'graphviz version (\d+\.\d+(?:\.\d+){,2}) ', out) - if ma is None: - raise RuntimeError('cannot parse %r output: %r' % (cmd, out)) - - return tuple(int(d) for d in ma.group(1).split('.')) - - -def view(filepath, quiet=False): - """Open filepath with its default viewing application (platform-specific). - - Args: - filepath: Path to the file to open in viewer. - quiet (bool): Suppress ``stderr`` output from the viewer process - (ineffective on Windows). - Raises: - RuntimeError: If the current platform is not supported. - """ - try: - view_func = getattr(view, PLATFORM) - except AttributeError: - raise RuntimeError('platform %r not supported' % PLATFORM) - view_func(filepath, quiet) - - -@tools.attach(view, 'darwin') -def view_darwin(filepath, quiet): - """Open filepath with its default application (mac).""" - cmd = ['open', filepath] - log.debug('view: %r', cmd) - popen_func = _compat.Popen_stderr_devnull if quiet else subprocess.Popen - popen_func(cmd) - - -@tools.attach(view, 'linux') -@tools.attach(view, 'freebsd') -def view_unixoid(filepath, quiet): - """Open filepath in the user's preferred application (linux, freebsd).""" - cmd = ['xdg-open', filepath] - log.debug('view: %r', cmd) - popen_func = _compat.Popen_stderr_devnull if quiet else subprocess.Popen - popen_func(cmd) - - -@tools.attach(view, 'windows') -def view_windows(filepath, quiet): - """Start filepath with its associated application (windows).""" - # TODO: implement quiet=True - filepath = os.path.normpath(filepath) - log.debug('view: %r', filepath) - os.startfile(filepath) diff --git a/src/graphviz/dot.py b/src/graphviz/dot.py deleted file mode 100644 index 40cf1ae..0000000 --- a/src/graphviz/dot.py +++ /dev/null @@ -1,287 +0,0 @@ -# dot.py - create dot code - -r"""Assemble DOT source code objects. - ->>> dot = Graph(comment=u'M\xf8nti Pyth\xf8n ik den H\xf8lie Grailen') - ->>> dot.node(u'M\xf8\xf8se') ->>> dot.node('trained_by', u'trained by') ->>> dot.node('tutte', u'TUTTE HERMSGERVORDENBROTBORDA') - ->>> dot.edge(u'M\xf8\xf8se', 'trained_by') ->>> dot.edge('trained_by', 'tutte') - ->>> dot.node_attr['shape'] = 'rectangle' - ->>> print(dot.source.replace(u'\xf8', '0')) #doctest: +NORMALIZE_WHITESPACE -// M0nti Pyth0n ik den H0lie Grailen -graph { - node [shape=rectangle] - "M00se" - trained_by [label="trained by"] - tutte [label="TUTTE HERMSGERVORDENBROTBORDA"] - "M00se" -- trained_by - trained_by -- tutte -} - ->>> dot.view('test-output/m00se.gv') # doctest: +SKIP -'test-output/m00se.gv.pdf' -""" - -from . import lang -from . import files - -__all__ = ['Graph', 'Digraph'] - - -class Dot(files.File): - """Assemble, save, and render DOT source code, open result in viewer.""" - - _comment = '// %s' - _subgraph = 'subgraph %s{' - _subgraph_plain = '%s{' - _node = _attr = '\t%s%s' - _attr_plain = _attr % ('%s', '') - _tail = '}' - - _quote = staticmethod(lang.quote) - _quote_edge = staticmethod(lang.quote_edge) - - _a_list = staticmethod(lang.a_list) - _attr_list = staticmethod(lang.attr_list) - - def __init__(self, name=None, comment=None, - filename=None, directory=None, - format=None, engine=None, encoding=files.ENCODING, - graph_attr=None, node_attr=None, edge_attr=None, body=None, - strict=False): - self.name = name - self.comment = comment - - super(Dot, self).__init__(filename, directory, format, engine, encoding) - - self.graph_attr = dict(graph_attr) if graph_attr is not None else {} - self.node_attr = dict(node_attr) if node_attr is not None else {} - self.edge_attr = dict(edge_attr) if edge_attr is not None else {} - - self.body = list(body) if body is not None else [] - - self.strict = strict - - def _kwargs(self): - result = super(Dot, self)._kwargs() - result.update(name=self.name, - comment=self.comment, - graph_attr=dict(self.graph_attr), - node_attr=dict(self.node_attr), - edge_attr=dict(self.edge_attr), - body=list(self.body), - strict=self.strict) - return result - - def clear(self, keep_attrs=False): - """Reset content to an empty body, clear graph/node/egde_attr mappings. - - Args: - keep_attrs (bool): preserve graph/node/egde_attr mappings - """ - if not keep_attrs: - for a in (self.graph_attr, self.node_attr, self.edge_attr): - a.clear() - del self.body[:] - - def __iter__(self, subgraph=False): - """Yield the DOT source code line by line (as graph or subgraph).""" - if self.comment: - yield self._comment % self.comment - - if subgraph: - if self.strict: - raise ValueError('subgraphs cannot be strict') - head = self._subgraph if self.name else self._subgraph_plain - else: - head = self._head_strict if self.strict else self._head - yield head % (self._quote(self.name) + ' ' if self.name else '') - - for kw in ('graph', 'node', 'edge'): - attrs = getattr(self, '%s_attr' % kw) - if attrs: - yield self._attr % (kw, self._attr_list(None, attrs)) - - for line in self.body: - yield line - - yield self._tail - - def __str__(self): - """The DOT source code as string.""" - return '\n'.join(self) - - source = property(__str__, doc=__str__.__doc__) - - def node(self, name, label=None, _attributes=None, **attrs): - """Create a node. - - Args: - name: Unique identifier for the node inside the source. - label: Caption to be displayed (defaults to the node ``name``). - attrs: Any additional node attributes (must be strings). - """ - name = self._quote(name) - attr_list = self._attr_list(label, attrs, _attributes) - line = self._node % (name, attr_list) - self.body.append(line) - - def edge(self, tail_name, head_name, label=None, _attributes=None, **attrs): - """Create an edge between two nodes. - - Args: - tail_name: Start node identifier. - head_name: End node identifier. - label: Caption to be displayed near the edge. - attrs: Any additional edge attributes (must be strings). - """ - tail_name = self._quote_edge(tail_name) - head_name = self._quote_edge(head_name) - attr_list = self._attr_list(label, attrs, _attributes) - line = self._edge % (tail_name, head_name, attr_list) - self.body.append(line) - - def edges(self, tail_head_iter): - """Create a bunch of edges. - - Args: - tail_head_iter: Iterable of ``(tail_name, head_name)`` pairs. - """ - edge = self._edge_plain - quote = self._quote_edge - lines = (edge % (quote(t), quote(h)) for t, h in tail_head_iter) - self.body.extend(lines) - - def attr(self, kw=None, _attributes=None, **attrs): - """Add a general or graph/node/edge attribute statement. - - Args: - kw: Attributes target (``None`` or ``'graph'``, ``'node'``, ``'edge'``). - attrs: Attributes to be set (must be strings, may be empty). - - See the :ref:`usage examples in the User Guide `. - """ - if kw is not None and kw.lower() not in ('graph', 'node', 'edge'): - raise ValueError('attr statement must target graph, node, or edge: ' - '%r' % kw) - if attrs or _attributes: - if kw is None: - a_list = self._a_list(None, attrs, _attributes) - line = self._attr_plain % a_list - else: - attr_list = self._attr_list(None, attrs, _attributes) - line = self._attr % (kw, attr_list) - self.body.append(line) - - def subgraph(self, graph=None, name=None, comment=None, - graph_attr=None, node_attr=None, edge_attr=None, body=None): - """Add the current content of the given sole ``graph`` argument as subgraph \ - or return a context manager returning a new graph instance created \ - with the given (``name``, ``comment``, etc.) arguments whose content is \ - added as subgraph when leaving the context manager's ``with``-block. - - Args: - graph: An instance of the same kind (:class:`.Graph`, :class:`.Digraph`) - as the current graph (sole argument in non-with-block use). - name: Subgraph name (``with``-block use). - comment: Subgraph comment (``with``-block use). - graph_attr: Subgraph-level attribute-value mapping (``with``-block use). - node_attr: Node-level attribute-value mapping (``with``-block use). - edge_attr: Edge-level attribute-value mapping (``with``-block use). - body: Verbatim lines to add to the subgraph ``body`` (``with``-block use). - - See the :ref:`usage examples in the User Guide `. - - .. note:: - If the ``name`` of the subgraph begins with ``'cluster'`` (all lowercase) - the layout engine will treat it as a special cluster subgraph. - """ - if graph is None: - return SubgraphContext(self, {'name': name, - 'comment': comment, - 'graph_attr': graph_attr, - 'node_attr': node_attr, - 'edge_attr': edge_attr, - 'body': body}) - - args = [name, comment, graph_attr, node_attr, edge_attr, body] - if not all(a is None for a in args): - raise ValueError('graph must be sole argument of subgraph()') - - if graph.directed != self.directed: - raise ValueError('%r cannot add subgraph of different kind:' - ' %r' % (self, graph)) - - lines = ['\t' + line for line in graph.__iter__(subgraph=True)] - self.body.extend(lines) - - -class SubgraphContext(object): - """Return a blank instance of the parent and add as subgraph on exit.""" - - def __init__(self, parent, kwargs): - self.parent = parent - self.graph = parent.__class__(**kwargs) - - def __enter__(self): - return self.graph - - def __exit__(self, type_, value, traceback): - if type_ is None: - self.parent.subgraph(self.graph) - - -class Graph(Dot): - """Graph source code in the DOT language. - - Args: - name: Graph name used in the source code. - comment: Comment added to the first line of the source. - filename: Filename for saving the source (defaults to ``name`` + ``'.gv'``). - directory: (Sub)directory for source saving and rendering. - format: Rendering output format (``'pdf'``, ``'png'``, ...). - engine: Layout command used (``'dot'``, ``'neato'``, ...). - encoding: Encoding for saving the source. - graph_attr: Mapping of ``(attribute, value)`` pairs for the graph. - node_attr: Mapping of ``(attribute, value)`` pairs set for all nodes. - edge_attr: Mapping of ``(attribute, value)`` pairs set for all edges. - body: Iterable of verbatim lines to add to the graph ``body``. - strict (bool): Rendering should merge multi-edges. - - Note: - All parameters are optional and can be changed under their - corresponding attribute name after instance creation. - """ - - _head = 'graph %s{' - _head_strict = 'strict %s' % _head - _edge = '\t%s -- %s%s' - _edge_plain = _edge % ('%s', '%s', '') - - @property - def directed(self): - """``False``""" - return False - - -class Digraph(Dot): - """Directed graph source code in the DOT language.""" - - if Graph.__doc__ is not None: - __doc__ += Graph.__doc__.partition('.')[2] - - _head = 'digraph %s{' - _head_strict = 'strict %s' % _head - _edge = '\t%s -> %s%s' - _edge_plain = _edge % ('%s', '%s', '') - - @property - def directed(self): - """``True``""" - return True diff --git a/src/graphviz/files.py b/src/graphviz/files.py deleted file mode 100644 index bf1585f..0000000 --- a/src/graphviz/files.py +++ /dev/null @@ -1,311 +0,0 @@ -# files.py - save, render, view - -"""Save DOT code objects, render with Graphviz dot, and open in viewer.""" - -import os -import io -import codecs -import locale -import logging - -from ._compat import text_type - -from . import backend -from . import tools - -__all__ = ['File', 'Source'] - -ENCODING = 'utf-8' - - -log = logging.getLogger(__name__) - - -class Base(object): - - _format = 'pdf' - _engine = 'dot' - _encoding = ENCODING - - @property - def format(self): - """The output format used for rendering (``'pdf'``, ``'png'``, ...).""" - return self._format - - @format.setter - def format(self, format): - format = format.lower() - if format not in backend.FORMATS: - raise ValueError('unknown format: %r' % format) - self._format = format - - @property - def engine(self): - """The layout commmand used for rendering (``'dot'``, ``'neato'``, ...).""" - return self._engine - - @engine.setter - def engine(self, engine): - engine = engine.lower() - if engine not in backend.ENGINES: - raise ValueError('unknown engine: %r' % engine) - self._engine = engine - - @property - def encoding(self): - """The encoding for the saved source file.""" - return self._encoding - - @encoding.setter - def encoding(self, encoding): - if encoding is None: - encoding = locale.getpreferredencoding() - codecs.lookup(encoding) # raise early - self._encoding = encoding - - def copy(self): - """Return a copied instance of the object. - - Returns: - An independent copy of the current object. - """ - kwargs = self._kwargs() - return self.__class__(**kwargs) - - def _kwargs(self): - ns = self.__dict__ - return {a[1:]: ns[a] for a in ('_format', '_engine', '_encoding') - if a in ns} - - -class File(Base): - - directory = '' - - _default_extension = 'gv' - - def __init__(self, filename=None, directory=None, - format=None, engine=None, encoding=ENCODING): - if filename is None: - name = getattr(self, 'name', None) or self.__class__.__name__ - filename = '%s.%s' % (name, self._default_extension) - self.filename = filename - - if directory is not None: - self.directory = directory - - if format is not None: - self.format = format - - if engine is not None: - self.engine = engine - - self.encoding = encoding - - def _kwargs(self): - result = super(File, self)._kwargs() - result['filename'] = self.filename - if 'directory' in self.__dict__: - result['directory'] = self.directory - return result - - def _repr_svg_(self): - return self.pipe(format='svg').decode(self._encoding) - - def pipe(self, format=None, renderer=None, formatter=None, quiet=False): - """Return the source piped through the Graphviz layout command. - - Args: - format: The output format used for rendering (``'pdf'``, ``'png'``, etc.). - renderer: The output renderer used for rendering (``'cairo'``, ``'gd'``, ...). - formatter: The output formatter used for rendering (``'cairo'``, ``'gd'``, ...). - quiet (bool): Suppress ``stderr`` output from the layout subprocess. - Returns: - Binary (encoded) stdout of the layout command. - Raises: - ValueError: If ``format``, ``renderer``, or ``formatter`` are not known. - graphviz.RequiredArgumentError: If ``formatter`` is given but ``renderer`` is None. - graphviz.ExecutableNotFound: If the Graphviz executable is not found. - subprocess.CalledProcessError: If the exit status is non-zero. - """ - if format is None: - format = self._format - - data = text_type(self.source).encode(self._encoding) - - out = backend.pipe(self._engine, format, data, - renderer=renderer, formatter=formatter, - quiet=quiet) - - return out - - @property - def filepath(self): - return os.path.join(self.directory, self.filename) - - def save(self, filename=None, directory=None): - """Save the DOT source to file. Ensure the file ends with a newline. - - Args: - filename: Filename for saving the source (defaults to ``name`` + ``'.gv'``) - directory: (Sub)directory for source saving and rendering. - Returns: - The (possibly relative) path of the saved source file. - """ - if filename is not None: - self.filename = filename - if directory is not None: - self.directory = directory - - filepath = self.filepath - tools.mkdirs(filepath) - - data = text_type(self.source) - - log.debug('write %d bytes to %r', len(data), filepath) - with io.open(filepath, 'w', encoding=self.encoding) as fd: - fd.write(data) - if not data.endswith(u'\n'): - fd.write(u'\n') - - return filepath - - def render(self, filename=None, directory=None, view=False, cleanup=False, - format=None, renderer=None, formatter=None, - quiet=False, quiet_view=False): - """Save the source to file and render with the Graphviz engine. - - Args: - filename: Filename for saving the source (defaults to ``name`` + ``'.gv'``) - directory: (Sub)directory for source saving and rendering. - view (bool): Open the rendered result with the default application. - cleanup (bool): Delete the source file after rendering. - format: The output format used for rendering (``'pdf'``, ``'png'``, etc.). - renderer: The output renderer used for rendering (``'cairo'``, ``'gd'``, ...). - formatter: The output formatter used for rendering (``'cairo'``, ``'gd'``, ...). - quiet (bool): Suppress ``stderr`` output from the layout subprocess. - quiet_view (bool): Suppress ``stderr`` output from the viewer process - (implies ``view=True``, ineffective on Windows). - Returns: - The (possibly relative) path of the rendered file. - Raises: - ValueError: If ``format``, ``renderer``, or ``formatter`` are not known. - graphviz.RequiredArgumentError: If ``formatter`` is given but ``renderer`` is None. - graphviz.ExecutableNotFound: If the Graphviz executable is not found. - subprocess.CalledProcessError: If the exit status is non-zero. - RuntimeError: If viewer opening is requested but not supported. - - The layout command is started from the directory of ``filepath``, so that - references to external files (e.g. ``[image=...]``) can be given as paths - relative to the DOT source file. - """ - filepath = self.save(filename, directory) - - if format is None: - format = self._format - - rendered = backend.render(self._engine, format, filepath, - renderer=renderer, formatter=formatter, - quiet=quiet) - - if cleanup: - log.debug('delete %r', filepath) - os.remove(filepath) - - if quiet_view or view: - self._view(rendered, self._format, quiet_view) - - return rendered - - def view(self, filename=None, directory=None, cleanup=False, - quiet=False, quiet_view=False): - """Save the source to file, open the rendered result in a viewer. - - Args: - filename: Filename for saving the source (defaults to ``name`` + ``'.gv'``) - directory: (Sub)directory for source saving and rendering. - cleanup (bool): Delete the source file after rendering. - quiet (bool): Suppress ``stderr`` output from the layout subprocess. - quiet_view (bool): Suppress ``stderr`` output from the viewer process - (ineffective on Windows). - Returns: - The (possibly relative) path of the rendered file. - Raises: - graphviz.ExecutableNotFound: If the Graphviz executable is not found. - subprocess.CalledProcessError: If the exit status is non-zero. - RuntimeError: If opening the viewer is not supported. - - Short-cut method for calling :meth:`.render` with ``view=True``. - """ - return self.render(filename=filename, directory=directory, - view=True, cleanup=cleanup, - quiet=quiet, quiet_view=quiet_view) - - def _view(self, filepath, format, quiet): - """Start the right viewer based on file format and platform.""" - methodnames = [ - '_view_%s_%s' % (format, backend.PLATFORM), - '_view_%s' % backend.PLATFORM, - ] - for name in methodnames: - view_method = getattr(self, name, None) - if view_method is not None: - break - else: - raise RuntimeError('%r has no built-in viewer support for %r' - ' on %r platform' % (self.__class__, format, - backend.PLATFORM)) - view_method(filepath, quiet) - - _view_darwin = staticmethod(backend.view.darwin) - _view_freebsd = staticmethod(backend.view.freebsd) - _view_linux = staticmethod(backend.view.linux) - _view_windows = staticmethod(backend.view.windows) - - -class Source(File): - """Verbatim DOT source code string to be rendered by Graphviz. - - Args: - source: The verbatim DOT source code string. - filename: Filename for saving the source (defaults to ``'Source.gv'``). - directory: (Sub)directory for source saving and rendering. - format: Rendering output format (``'pdf'``, ``'png'``, ...). - engine: Layout command used (``'dot'``, ``'neato'``, ...). - encoding: Encoding for saving the source. - - Note: - All parameters except ``source`` are optional. All of them can be changed - under their corresponding attribute name after instance creation. - """ - - @classmethod - def from_file(cls, filename, directory=None, - format=None, engine=None, encoding=ENCODING): - """Return an instance with the source string read from the given file. - - Args: - filename: Filename for loading/saving the source. - directory: (Sub)directory for source loading/saving and rendering. - format: Rendering output format (``'pdf'``, ``'png'``, ...). - engine: Layout command used (``'dot'``, ``'neato'``, ...). - encoding: Encoding for loading/saving the source. - """ - filepath = os.path.join(directory or '', filename) - if encoding is None: - encoding = locale.getpreferredencoding() - log.debug('read %r with encoding %r', filepath, encoding) - with io.open(filepath, encoding=encoding) as fd: - source = fd.read() - return cls(source, filename, directory, format, engine, encoding) - - def __init__(self, source, filename=None, directory=None, - format=None, engine=None, encoding=ENCODING): - super(Source, self).__init__(filename, directory, - format, engine, encoding) - self.source = source #: The verbatim DOT source code string. - - def _kwargs(self): - result = super(Source, self)._kwargs() - result['source'] = self.source - return result diff --git a/src/graphviz/lang.py b/src/graphviz/lang.py deleted file mode 100644 index 8969700..0000000 --- a/src/graphviz/lang.py +++ /dev/null @@ -1,195 +0,0 @@ -# lang.py - dot language creation helpers - -"""Quote strings to be valid DOT identifiers, assemble attribute lists.""" - -import re -import collections -import functools - -from . import _compat - -from . import tools - -__all__ = ['quote', 'quote_edge', 'a_list', 'attr_list', 'escape', 'nohtml'] - -# https://www.graphviz.org/doc/info/lang.html -# https://www.graphviz.org/doc/info/attrs.html#k:escString - -HTML_STRING = re.compile(r'<.*>$', re.DOTALL) - -ID = re.compile(r'([a-zA-Z_][a-zA-Z0-9_]*|-?(\.[0-9]+|[0-9]+(\.[0-9]*)?))$') - -KEYWORDS = {'node', 'edge', 'graph', 'digraph', 'subgraph', 'strict'} - -COMPASS = {'n', 'ne', 'e', 'se', 's', 'sw', 'w', 'nw', 'c', '_'} # TODO - -QUOTE_OPTIONAL_BACKSLASHES = re.compile(r'(?P(?:\\\\)*)' - r'\\?(?P")') - -ESCAPE_UNESCAPED_QUOTES = functools.partial(QUOTE_OPTIONAL_BACKSLASHES.sub, - r'\g\\\g') - - -def quote(identifier, - is_html_string=HTML_STRING.match, - is_valid_id=ID.match, dot_keywords=KEYWORDS, - escape_unescaped_quotes=ESCAPE_UNESCAPED_QUOTES): - r"""Return DOT identifier from string, quote if needed. - - >>> quote('') - '""' - - >>> quote('spam') - 'spam' - - >>> quote('spam spam') - '"spam spam"' - - >>> quote('-4.2') - '-4.2' - - >>> quote('.42') - '.42' - - >>> quote('<spam>') - '<spam>' - - >>> quote(nohtml('<>')) - '"<>"' - - >>> print(quote('"')) - "\"" - - >>> print(quote('\\"')) - "\"" - - >>> print(quote('\\\\"')) - "\\\"" - - >>> print(quote('\\\\\\"')) - "\\\"" - """ - if is_html_string(identifier) and not isinstance(identifier, NoHtml): - pass - elif not is_valid_id(identifier) or identifier.lower() in dot_keywords: - return '"%s"' % escape_unescaped_quotes(identifier) - return identifier - - -def quote_edge(identifier): - """Return DOT edge statement node_id from string, quote if needed. - - >>> quote_edge('spam') - 'spam' - - >>> quote_edge('spam spam:eggs eggs') - '"spam spam":"eggs eggs"' - - >>> quote_edge('spam:eggs:s') - 'spam:eggs:s' - """ - node, _, rest = identifier.partition(':') - parts = [quote(node)] - if rest: - port, _, compass = rest.partition(':') - parts.append(quote(port)) - if compass: - parts.append(compass) - return ':'.join(parts) - - -def a_list(label=None, kwargs=None, attributes=None): - """Return assembled DOT a_list string. - - >>> a_list('spam', {'spam': None, 'ham': 'ham ham', 'eggs': ''}) - 'label=spam eggs="" ham="ham ham"' - """ - result = ['label=%s' % quote(label)] if label is not None else [] - if kwargs: - items = ['%s=%s' % (quote(k), quote(v)) - for k, v in tools.mapping_items(kwargs) if v is not None] - result.extend(items) - if attributes: - if hasattr(attributes, 'items'): - attributes = tools.mapping_items(attributes) - items = ['%s=%s' % (quote(k), quote(v)) - for k, v in attributes if v is not None] - result.extend(items) - return ' '.join(result) - - -def attr_list(label=None, kwargs=None, attributes=None): - """Return assembled DOT attribute list string. - - Sorts ``kwargs`` and ``attributes`` if they are plain dicts (to avoid - unpredictable order from hash randomization in Python 3 versions). - - >>> attr_list() - '' - - >>> attr_list('spam spam', kwargs={'eggs': 'eggs', 'ham': 'ham ham'}) - ' [label="spam spam" eggs=eggs ham="ham ham"]' - - >>> attr_list(kwargs={'spam': None, 'eggs': ''}) - ' [eggs=""]' - """ - content = a_list(label, kwargs, attributes) - if not content: - return '' - return ' [%s]' % content - - -def escape(s): - r"""Return ``s`` as literal disabling special meaning of backslashes and ``'<...>'``. - - see also https://www.graphviz.org/doc/info/attrs.html#k:escString - - Args: - s: String in which backslashes and ``'<...>'`` should be treated as literal. - Raises: - TypeError: If ``s`` is not a ``str`` on Python 3, or a ``str``/``unicode`` on Python 2. - - >>> print(escape(r'\l')) - \\l - """ - return nohtml(s.replace('\\', '\\\\')) - - -class NoHtml(object): - """Mixin for string subclasses disabling fall-through of ``'<...>'``.""" - - __slots__ = () - - _doc = "%s subclass that does not treat ``'<...>'`` as DOT HTML string." - - @classmethod - def _subcls(cls, other): - name = '%s_%s' % (cls.__name__, other.__name__) - bases = (other, cls) - ns = {'__doc__': cls._doc % other.__name__} - return type(name, bases, ns) - - -NOHTML = collections.OrderedDict((c, NoHtml._subcls(c)) for c in _compat.string_classes) - - -def nohtml(s): - """Return copy of ``s`` that will not treat ``'<...>'`` as DOT HTML string in quoting. - - Args: - s: String in which leading ``'<'`` and trailing ``'>'`` should be treated as literal. - Raises: - TypeError: If ``s`` is not a ``str`` on Python 3, or a ``str``/``unicode`` on Python 2. - - >>> quote('<>-*-<>') - '<>-*-<>' - - >>> quote(nohtml('<>-*-<>')) - '"<>-*-<>"' - """ - try: - subcls = NOHTML[type(s)] - except KeyError: - raise TypeError('%r does not have one of the required types:' - ' %r' % (s, list(NOHTML))) - return subcls(s) diff --git a/src/graphviz/tools.py b/src/graphviz/tools.py deleted file mode 100644 index ef435b7..0000000 --- a/src/graphviz/tools.py +++ /dev/null @@ -1,47 +0,0 @@ -# tools.py - generic helpers - -import os - -from . import _compat - -__all__ = ['attach', 'mkdirs', 'mapping_items'] - - -def attach(object, name): - """Return a decorator doing ``setattr(object, name)`` with its argument. - - >>> spam = type('Spam', (object,), {})() - >>> @attach(spam, 'eggs') - ... def func(): - ... pass - >>> spam.eggs # doctest: +ELLIPSIS - - """ - def decorator(func): - setattr(object, name, func) - return func - return decorator - - -def mkdirs(filename, mode=0o777): - """Recursively create directories up to the path of ``filename`` as needed.""" - dirname = os.path.dirname(filename) - if not dirname: - return - _compat.makedirs(dirname, mode=mode, exist_ok=True) - - -def mapping_items(mapping): - """Return an iterator over the ``mapping`` items, sort if it's a plain dict. - - >>> list(mapping_items({'spam': 0, 'ham': 1, 'eggs': 2})) - [('eggs', 2), ('ham', 1), ('spam', 0)] - - >>> from collections import OrderedDict - >>> list(mapping_items(OrderedDict(enumerate(['spam', 'ham', 'eggs'])))) - [(0, 'spam'), (1, 'ham'), (2, 'eggs')] - """ - result = _compat.iteritems(mapping) - if type(mapping) is dict: - result = iter(sorted(result)) - return result diff --git a/src/wireviz/__init__.py b/src/wireviz/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/wireviz/build_examples.py b/src/wireviz/build_examples.py new file mode 100644 index 0000000..d989ae1 --- /dev/null +++ b/src/wireviz/build_examples.py @@ -0,0 +1,54 @@ +import wireviz +import os + +demos = 2 # 2 +<<<<<<< HEAD:src/wireviz/batch.py +examples = 9 # 9 +======= +examples = 6 # 6 +>>>>>>> 2d428e8... refactor dependencies and installation:src/wireviz/build_examples.py +tutorials = 7 # 7 + +if demos: + for i in range(1,demos+1): + fn = '../examples/demo{:02d}.yml'.format(i) + print(fn) + wireviz.parse(fn, gen_bom=True) + +if examples: + with open(os.path.abspath('../examples/readme.md'), 'w') as file: + file.write('# Example gallery\n') + for i in range(1,examples+1): + fn = '../examples/ex{:02d}.yml'.format(i) + print(fn) + wireviz.parse(fn, gen_bom=True) + + file.write('## Example {:02d}\n'.format(i)) + file.write('![](ex{:02d}.png)\n\n'.format(i)) + file.write('[Source](ex{:02d}.yml) - [Bill of Materials](ex{:02d}.bom.tsv)\n\n\n'.format(i,i)) + +if tutorials: + with open(os.path.abspath('../tutorial/readme.md'), 'w') as file: + file.write('# WireViz Tutorial\n') + for i in range(1,tutorials+1): + fn = '../tutorial/tutorial{:02d}.yml'.format(i) + print(fn) + wireviz.parse(fn, gen_bom=True) + + with open(os.path.abspath('../tutorial/tutorial{:02d}.md'.format(i)), 'r') as info: + for line in info: + file.write(line.replace('## ', '## {} - '.format(i))) + file.write('\n[Source](tutorial{:02d}.yml):\n\n'.format(i)) + + with open(os.path.abspath('../tutorial/tutorial{:02d}.yml'.format(i)), 'r') as src: + file.write('```yaml\n') + for line in src: + file.write(line) + file.write('```\n') + file.write('\n') + + file.write('\nOutput:\n\n'.format(i)) + + file.write('![](tutorial{:02d}.png)\n\n'.format(i)) + + file.write('[Bill of Materials](tutorial{:02d}.bom.tsv)\n\n\n'.format(i)) diff --git a/src/wireviz/wireviz.py b/src/wireviz/wireviz.py index 2be00a2..ceb350a 100755 --- a/src/wireviz/wireviz.py +++ b/src/wireviz/wireviz.py @@ -1,4 +1,6 @@ #!/usr/bin/env python3 + +import argparse import os from dataclasses import dataclass, field from typing import Any, List @@ -6,8 +8,8 @@ from collections import Counter import yaml from graphviz import Graph -import wv_colors -from wv_helper import nested, int2tuple, awg_equiv, flatten2d, tuplelist2tsv +from wireviz import wv_colors +from wireviz.wv_helper import nested, int2tuple, awg_equiv, flatten2d, tuplelist2tsv class Harness: @@ -620,8 +622,7 @@ def parse(file_in, file_out=None, gen_bom=False): h.output(filename=file_out, format=('png','svg'), gen_bom=gen_bom, view=False) -if __name__ == '__main__': - import argparse +def main(): ap = argparse.ArgumentParser() ap.add_argument('file_input', nargs='?', default='_test/test.yml') ap.add_argument('file_output', nargs='?', default=None) @@ -629,3 +630,6 @@ if __name__ == '__main__': args = ap.parse_args() parse(args.file_input, file_out=args.file_output, gen_bom=args.bom) + +if __name__ == '__main__': + main() diff --git a/src/yaml/__init__.py b/src/yaml/__init__.py deleted file mode 100644 index 13d687c..0000000 --- a/src/yaml/__init__.py +++ /dev/null @@ -1,427 +0,0 @@ - -from .error import * - -from .tokens import * -from .events import * -from .nodes import * - -from .loader import * -from .dumper import * - -__version__ = '5.3.1' -try: - from .cyaml import * - __with_libyaml__ = True -except ImportError: - __with_libyaml__ = False - -import io - -#------------------------------------------------------------------------------ -# Warnings control -#------------------------------------------------------------------------------ - -# 'Global' warnings state: -_warnings_enabled = { - 'YAMLLoadWarning': True, -} - -# Get or set global warnings' state -def warnings(settings=None): - if settings is None: - return _warnings_enabled - - if type(settings) is dict: - for key in settings: - if key in _warnings_enabled: - _warnings_enabled[key] = settings[key] - -# Warn when load() is called without Loader=... -class YAMLLoadWarning(RuntimeWarning): - pass - -def load_warning(method): - if _warnings_enabled['YAMLLoadWarning'] is False: - return - - import warnings - - message = ( - "calling yaml.%s() without Loader=... is deprecated, as the " - "default Loader is unsafe. Please read " - "https://msg.pyyaml.org/load for full details." - ) % method - - warnings.warn(message, YAMLLoadWarning, stacklevel=3) - -#------------------------------------------------------------------------------ -def scan(stream, Loader=Loader): - """ - Scan a YAML stream and produce scanning tokens. - """ - loader = Loader(stream) - try: - while loader.check_token(): - yield loader.get_token() - finally: - loader.dispose() - -def parse(stream, Loader=Loader): - """ - Parse a YAML stream and produce parsing events. - """ - loader = Loader(stream) - try: - while loader.check_event(): - yield loader.get_event() - finally: - loader.dispose() - -def compose(stream, Loader=Loader): - """ - Parse the first YAML document in a stream - and produce the corresponding representation tree. - """ - loader = Loader(stream) - try: - return loader.get_single_node() - finally: - loader.dispose() - -def compose_all(stream, Loader=Loader): - """ - Parse all YAML documents in a stream - and produce corresponding representation trees. - """ - loader = Loader(stream) - try: - while loader.check_node(): - yield loader.get_node() - finally: - loader.dispose() - -def load(stream, Loader=None): - """ - Parse the first YAML document in a stream - and produce the corresponding Python object. - """ - if Loader is None: - load_warning('load') - Loader = FullLoader - - loader = Loader(stream) - try: - return loader.get_single_data() - finally: - loader.dispose() - -def load_all(stream, Loader=None): - """ - Parse all YAML documents in a stream - and produce corresponding Python objects. - """ - if Loader is None: - load_warning('load_all') - Loader = FullLoader - - loader = Loader(stream) - try: - while loader.check_data(): - yield loader.get_data() - finally: - loader.dispose() - -def full_load(stream): - """ - Parse the first YAML document in a stream - and produce the corresponding Python object. - - Resolve all tags except those known to be - unsafe on untrusted input. - """ - return load(stream, FullLoader) - -def full_load_all(stream): - """ - Parse all YAML documents in a stream - and produce corresponding Python objects. - - Resolve all tags except those known to be - unsafe on untrusted input. - """ - return load_all(stream, FullLoader) - -def safe_load(stream): - """ - Parse the first YAML document in a stream - and produce the corresponding Python object. - - Resolve only basic YAML tags. This is known - to be safe for untrusted input. - """ - return load(stream, SafeLoader) - -def safe_load_all(stream): - """ - Parse all YAML documents in a stream - and produce corresponding Python objects. - - Resolve only basic YAML tags. This is known - to be safe for untrusted input. - """ - return load_all(stream, SafeLoader) - -def unsafe_load(stream): - """ - Parse the first YAML document in a stream - and produce the corresponding Python object. - - Resolve all tags, even those known to be - unsafe on untrusted input. - """ - return load(stream, UnsafeLoader) - -def unsafe_load_all(stream): - """ - Parse all YAML documents in a stream - and produce corresponding Python objects. - - Resolve all tags, even those known to be - unsafe on untrusted input. - """ - return load_all(stream, UnsafeLoader) - -def emit(events, stream=None, Dumper=Dumper, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None): - """ - Emit YAML parsing events into a stream. - If stream is None, return the produced string instead. - """ - getvalue = None - if stream is None: - stream = io.StringIO() - getvalue = stream.getvalue - dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, - allow_unicode=allow_unicode, line_break=line_break) - try: - for event in events: - dumper.emit(event) - finally: - dumper.dispose() - if getvalue: - return getvalue() - -def serialize_all(nodes, stream=None, Dumper=Dumper, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None): - """ - Serialize a sequence of representation trees into a YAML stream. - If stream is None, return the produced string instead. - """ - getvalue = None - if stream is None: - if encoding is None: - stream = io.StringIO() - else: - stream = io.BytesIO() - getvalue = stream.getvalue - dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, - allow_unicode=allow_unicode, line_break=line_break, - encoding=encoding, version=version, tags=tags, - explicit_start=explicit_start, explicit_end=explicit_end) - try: - dumper.open() - for node in nodes: - dumper.serialize(node) - dumper.close() - finally: - dumper.dispose() - if getvalue: - return getvalue() - -def serialize(node, stream=None, Dumper=Dumper, **kwds): - """ - Serialize a representation tree into a YAML stream. - If stream is None, return the produced string instead. - """ - return serialize_all([node], stream, Dumper=Dumper, **kwds) - -def dump_all(documents, stream=None, Dumper=Dumper, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - """ - Serialize a sequence of Python objects into a YAML stream. - If stream is None, return the produced string instead. - """ - getvalue = None - if stream is None: - if encoding is None: - stream = io.StringIO() - else: - stream = io.BytesIO() - getvalue = stream.getvalue - dumper = Dumper(stream, default_style=default_style, - default_flow_style=default_flow_style, - canonical=canonical, indent=indent, width=width, - allow_unicode=allow_unicode, line_break=line_break, - encoding=encoding, version=version, tags=tags, - explicit_start=explicit_start, explicit_end=explicit_end, sort_keys=sort_keys) - try: - dumper.open() - for data in documents: - dumper.represent(data) - dumper.close() - finally: - dumper.dispose() - if getvalue: - return getvalue() - -def dump(data, stream=None, Dumper=Dumper, **kwds): - """ - Serialize a Python object into a YAML stream. - If stream is None, return the produced string instead. - """ - return dump_all([data], stream, Dumper=Dumper, **kwds) - -def safe_dump_all(documents, stream=None, **kwds): - """ - Serialize a sequence of Python objects into a YAML stream. - Produce only basic YAML tags. - If stream is None, return the produced string instead. - """ - return dump_all(documents, stream, Dumper=SafeDumper, **kwds) - -def safe_dump(data, stream=None, **kwds): - """ - Serialize a Python object into a YAML stream. - Produce only basic YAML tags. - If stream is None, return the produced string instead. - """ - return dump_all([data], stream, Dumper=SafeDumper, **kwds) - -def add_implicit_resolver(tag, regexp, first=None, - Loader=None, Dumper=Dumper): - """ - Add an implicit scalar detector. - If an implicit scalar value matches the given regexp, - the corresponding tag is assigned to the scalar. - first is a sequence of possible initial characters or None. - """ - if Loader is None: - loader.Loader.add_implicit_resolver(tag, regexp, first) - loader.FullLoader.add_implicit_resolver(tag, regexp, first) - loader.UnsafeLoader.add_implicit_resolver(tag, regexp, first) - else: - Loader.add_implicit_resolver(tag, regexp, first) - Dumper.add_implicit_resolver(tag, regexp, first) - -def add_path_resolver(tag, path, kind=None, Loader=None, Dumper=Dumper): - """ - Add a path based resolver for the given tag. - A path is a list of keys that forms a path - to a node in the representation tree. - Keys can be string values, integers, or None. - """ - if Loader is None: - loader.Loader.add_path_resolver(tag, path, kind) - loader.FullLoader.add_path_resolver(tag, path, kind) - loader.UnsafeLoader.add_path_resolver(tag, path, kind) - else: - Loader.add_path_resolver(tag, path, kind) - Dumper.add_path_resolver(tag, path, kind) - -def add_constructor(tag, constructor, Loader=None): - """ - Add a constructor for the given tag. - Constructor is a function that accepts a Loader instance - and a node object and produces the corresponding Python object. - """ - if Loader is None: - loader.Loader.add_constructor(tag, constructor) - loader.FullLoader.add_constructor(tag, constructor) - loader.UnsafeLoader.add_constructor(tag, constructor) - else: - Loader.add_constructor(tag, constructor) - -def add_multi_constructor(tag_prefix, multi_constructor, Loader=None): - """ - Add a multi-constructor for the given tag prefix. - Multi-constructor is called for a node if its tag starts with tag_prefix. - Multi-constructor accepts a Loader instance, a tag suffix, - and a node object and produces the corresponding Python object. - """ - if Loader is None: - loader.Loader.add_multi_constructor(tag_prefix, multi_constructor) - loader.FullLoader.add_multi_constructor(tag_prefix, multi_constructor) - loader.UnsafeLoader.add_multi_constructor(tag_prefix, multi_constructor) - else: - Loader.add_multi_constructor(tag_prefix, multi_constructor) - -def add_representer(data_type, representer, Dumper=Dumper): - """ - Add a representer for the given type. - Representer is a function accepting a Dumper instance - and an instance of the given data type - and producing the corresponding representation node. - """ - Dumper.add_representer(data_type, representer) - -def add_multi_representer(data_type, multi_representer, Dumper=Dumper): - """ - Add a representer for the given type. - Multi-representer is a function accepting a Dumper instance - and an instance of the given data type or subtype - and producing the corresponding representation node. - """ - Dumper.add_multi_representer(data_type, multi_representer) - -class YAMLObjectMetaclass(type): - """ - The metaclass for YAMLObject. - """ - def __init__(cls, name, bases, kwds): - super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds) - if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None: - if isinstance(cls.yaml_loader, list): - for loader in cls.yaml_loader: - loader.add_constructor(cls.yaml_tag, cls.from_yaml) - else: - cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml) - - cls.yaml_dumper.add_representer(cls, cls.to_yaml) - -class YAMLObject(metaclass=YAMLObjectMetaclass): - """ - An object that can dump itself to a YAML stream - and load itself from a YAML stream. - """ - - __slots__ = () # no direct instantiation, so allow immutable subclasses - - yaml_loader = [Loader, FullLoader, UnsafeLoader] - yaml_dumper = Dumper - - yaml_tag = None - yaml_flow_style = None - - @classmethod - def from_yaml(cls, loader, node): - """ - Convert a representation node to a Python object. - """ - return loader.construct_yaml_object(node, cls) - - @classmethod - def to_yaml(cls, dumper, data): - """ - Convert a Python object to a representation node. - """ - return dumper.represent_yaml_object(cls.yaml_tag, data, cls, - flow_style=cls.yaml_flow_style) - diff --git a/src/yaml/composer.py b/src/yaml/composer.py deleted file mode 100644 index 6d15cb4..0000000 --- a/src/yaml/composer.py +++ /dev/null @@ -1,139 +0,0 @@ - -__all__ = ['Composer', 'ComposerError'] - -from .error import MarkedYAMLError -from .events import * -from .nodes import * - -class ComposerError(MarkedYAMLError): - pass - -class Composer: - - def __init__(self): - self.anchors = {} - - def check_node(self): - # Drop the STREAM-START event. - if self.check_event(StreamStartEvent): - self.get_event() - - # If there are more documents available? - return not self.check_event(StreamEndEvent) - - def get_node(self): - # Get the root node of the next document. - if not self.check_event(StreamEndEvent): - return self.compose_document() - - def get_single_node(self): - # Drop the STREAM-START event. - self.get_event() - - # Compose a document if the stream is not empty. - document = None - if not self.check_event(StreamEndEvent): - document = self.compose_document() - - # Ensure that the stream contains no more documents. - if not self.check_event(StreamEndEvent): - event = self.get_event() - raise ComposerError("expected a single document in the stream", - document.start_mark, "but found another document", - event.start_mark) - - # Drop the STREAM-END event. - self.get_event() - - return document - - def compose_document(self): - # Drop the DOCUMENT-START event. - self.get_event() - - # Compose the root node. - node = self.compose_node(None, None) - - # Drop the DOCUMENT-END event. - self.get_event() - - self.anchors = {} - return node - - def compose_node(self, parent, index): - if self.check_event(AliasEvent): - event = self.get_event() - anchor = event.anchor - if anchor not in self.anchors: - raise ComposerError(None, None, "found undefined alias %r" - % anchor, event.start_mark) - return self.anchors[anchor] - event = self.peek_event() - anchor = event.anchor - if anchor is not None: - if anchor in self.anchors: - raise ComposerError("found duplicate anchor %r; first occurrence" - % anchor, self.anchors[anchor].start_mark, - "second occurrence", event.start_mark) - self.descend_resolver(parent, index) - if self.check_event(ScalarEvent): - node = self.compose_scalar_node(anchor) - elif self.check_event(SequenceStartEvent): - node = self.compose_sequence_node(anchor) - elif self.check_event(MappingStartEvent): - node = self.compose_mapping_node(anchor) - self.ascend_resolver() - return node - - def compose_scalar_node(self, anchor): - event = self.get_event() - tag = event.tag - if tag is None or tag == '!': - tag = self.resolve(ScalarNode, event.value, event.implicit) - node = ScalarNode(tag, event.value, - event.start_mark, event.end_mark, style=event.style) - if anchor is not None: - self.anchors[anchor] = node - return node - - def compose_sequence_node(self, anchor): - start_event = self.get_event() - tag = start_event.tag - if tag is None or tag == '!': - tag = self.resolve(SequenceNode, None, start_event.implicit) - node = SequenceNode(tag, [], - start_event.start_mark, None, - flow_style=start_event.flow_style) - if anchor is not None: - self.anchors[anchor] = node - index = 0 - while not self.check_event(SequenceEndEvent): - node.value.append(self.compose_node(node, index)) - index += 1 - end_event = self.get_event() - node.end_mark = end_event.end_mark - return node - - def compose_mapping_node(self, anchor): - start_event = self.get_event() - tag = start_event.tag - if tag is None or tag == '!': - tag = self.resolve(MappingNode, None, start_event.implicit) - node = MappingNode(tag, [], - start_event.start_mark, None, - flow_style=start_event.flow_style) - if anchor is not None: - self.anchors[anchor] = node - while not self.check_event(MappingEndEvent): - #key_event = self.peek_event() - item_key = self.compose_node(node, None) - #if item_key in node.value: - # raise ComposerError("while composing a mapping", start_event.start_mark, - # "found duplicate key", key_event.start_mark) - item_value = self.compose_node(node, item_key) - #node.value[item_key] = item_value - node.value.append((item_key, item_value)) - end_event = self.get_event() - node.end_mark = end_event.end_mark - return node - diff --git a/src/yaml/constructor.py b/src/yaml/constructor.py deleted file mode 100644 index 1948b12..0000000 --- a/src/yaml/constructor.py +++ /dev/null @@ -1,748 +0,0 @@ - -__all__ = [ - 'BaseConstructor', - 'SafeConstructor', - 'FullConstructor', - 'UnsafeConstructor', - 'Constructor', - 'ConstructorError' -] - -from .error import * -from .nodes import * - -import collections.abc, datetime, base64, binascii, re, sys, types - -class ConstructorError(MarkedYAMLError): - pass - -class BaseConstructor: - - yaml_constructors = {} - yaml_multi_constructors = {} - - def __init__(self): - self.constructed_objects = {} - self.recursive_objects = {} - self.state_generators = [] - self.deep_construct = False - - def check_data(self): - # If there are more documents available? - return self.check_node() - - def check_state_key(self, key): - """Block special attributes/methods from being set in a newly created - object, to prevent user-controlled methods from being called during - deserialization""" - if self.get_state_keys_blacklist_regexp().match(key): - raise ConstructorError(None, None, - "blacklisted key '%s' in instance state found" % (key,), None) - - def get_data(self): - # Construct and return the next document. - if self.check_node(): - return self.construct_document(self.get_node()) - - def get_single_data(self): - # Ensure that the stream contains a single document and construct it. - node = self.get_single_node() - if node is not None: - return self.construct_document(node) - return None - - def construct_document(self, node): - data = self.construct_object(node) - while self.state_generators: - state_generators = self.state_generators - self.state_generators = [] - for generator in state_generators: - for dummy in generator: - pass - self.constructed_objects = {} - self.recursive_objects = {} - self.deep_construct = False - return data - - def construct_object(self, node, deep=False): - if node in self.constructed_objects: - return self.constructed_objects[node] - if deep: - old_deep = self.deep_construct - self.deep_construct = True - if node in self.recursive_objects: - raise ConstructorError(None, None, - "found unconstructable recursive node", node.start_mark) - self.recursive_objects[node] = None - constructor = None - tag_suffix = None - if node.tag in self.yaml_constructors: - constructor = self.yaml_constructors[node.tag] - else: - for tag_prefix in self.yaml_multi_constructors: - if tag_prefix is not None and node.tag.startswith(tag_prefix): - tag_suffix = node.tag[len(tag_prefix):] - constructor = self.yaml_multi_constructors[tag_prefix] - break - else: - if None in self.yaml_multi_constructors: - tag_suffix = node.tag - constructor = self.yaml_multi_constructors[None] - elif None in self.yaml_constructors: - constructor = self.yaml_constructors[None] - elif isinstance(node, ScalarNode): - constructor = self.__class__.construct_scalar - elif isinstance(node, SequenceNode): - constructor = self.__class__.construct_sequence - elif isinstance(node, MappingNode): - constructor = self.__class__.construct_mapping - if tag_suffix is None: - data = constructor(self, node) - else: - data = constructor(self, tag_suffix, node) - if isinstance(data, types.GeneratorType): - generator = data - data = next(generator) - if self.deep_construct: - for dummy in generator: - pass - else: - self.state_generators.append(generator) - self.constructed_objects[node] = data - del self.recursive_objects[node] - if deep: - self.deep_construct = old_deep - return data - - def construct_scalar(self, node): - if not isinstance(node, ScalarNode): - raise ConstructorError(None, None, - "expected a scalar node, but found %s" % node.id, - node.start_mark) - return node.value - - def construct_sequence(self, node, deep=False): - if not isinstance(node, SequenceNode): - raise ConstructorError(None, None, - "expected a sequence node, but found %s" % node.id, - node.start_mark) - return [self.construct_object(child, deep=deep) - for child in node.value] - - def construct_mapping(self, node, deep=False): - if not isinstance(node, MappingNode): - raise ConstructorError(None, None, - "expected a mapping node, but found %s" % node.id, - node.start_mark) - mapping = {} - for key_node, value_node in node.value: - key = self.construct_object(key_node, deep=deep) - if not isinstance(key, collections.abc.Hashable): - raise ConstructorError("while constructing a mapping", node.start_mark, - "found unhashable key", key_node.start_mark) - value = self.construct_object(value_node, deep=deep) - mapping[key] = value - return mapping - - def construct_pairs(self, node, deep=False): - if not isinstance(node, MappingNode): - raise ConstructorError(None, None, - "expected a mapping node, but found %s" % node.id, - node.start_mark) - pairs = [] - for key_node, value_node in node.value: - key = self.construct_object(key_node, deep=deep) - value = self.construct_object(value_node, deep=deep) - pairs.append((key, value)) - return pairs - - @classmethod - def add_constructor(cls, tag, constructor): - if not 'yaml_constructors' in cls.__dict__: - cls.yaml_constructors = cls.yaml_constructors.copy() - cls.yaml_constructors[tag] = constructor - - @classmethod - def add_multi_constructor(cls, tag_prefix, multi_constructor): - if not 'yaml_multi_constructors' in cls.__dict__: - cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy() - cls.yaml_multi_constructors[tag_prefix] = multi_constructor - -class SafeConstructor(BaseConstructor): - - def construct_scalar(self, node): - if isinstance(node, MappingNode): - for key_node, value_node in node.value: - if key_node.tag == 'tag:yaml.org,2002:value': - return self.construct_scalar(value_node) - return super().construct_scalar(node) - - def flatten_mapping(self, node): - merge = [] - index = 0 - while index < len(node.value): - key_node, value_node = node.value[index] - if key_node.tag == 'tag:yaml.org,2002:merge': - del node.value[index] - if isinstance(value_node, MappingNode): - self.flatten_mapping(value_node) - merge.extend(value_node.value) - elif isinstance(value_node, SequenceNode): - submerge = [] - for subnode in value_node.value: - if not isinstance(subnode, MappingNode): - raise ConstructorError("while constructing a mapping", - node.start_mark, - "expected a mapping for merging, but found %s" - % subnode.id, subnode.start_mark) - self.flatten_mapping(subnode) - submerge.append(subnode.value) - submerge.reverse() - for value in submerge: - merge.extend(value) - else: - raise ConstructorError("while constructing a mapping", node.start_mark, - "expected a mapping or list of mappings for merging, but found %s" - % value_node.id, value_node.start_mark) - elif key_node.tag == 'tag:yaml.org,2002:value': - key_node.tag = 'tag:yaml.org,2002:str' - index += 1 - else: - index += 1 - if merge: - node.value = merge + node.value - - def construct_mapping(self, node, deep=False): - if isinstance(node, MappingNode): - self.flatten_mapping(node) - return super().construct_mapping(node, deep=deep) - - def construct_yaml_null(self, node): - self.construct_scalar(node) - return None - - bool_values = { - 'yes': True, - 'no': False, - 'true': True, - 'false': False, - 'on': True, - 'off': False, - } - - def construct_yaml_bool(self, node): - value = self.construct_scalar(node) - return self.bool_values[value.lower()] - - def construct_yaml_int(self, node): - value = self.construct_scalar(node) - value = value.replace('_', '') - sign = +1 - if value[0] == '-': - sign = -1 - if value[0] in '+-': - value = value[1:] - if value == '0': - return 0 - elif value.startswith('0b'): - return sign*int(value[2:], 2) - elif value.startswith('0x'): - return sign*int(value[2:], 16) - elif value[0] == '0': - return sign*int(value, 8) - elif ':' in value: - digits = [int(part) for part in value.split(':')] - digits.reverse() - base = 1 - value = 0 - for digit in digits: - value += digit*base - base *= 60 - return sign*value - else: - return sign*int(value) - - inf_value = 1e300 - while inf_value != inf_value*inf_value: - inf_value *= inf_value - nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99). - - def construct_yaml_float(self, node): - value = self.construct_scalar(node) - value = value.replace('_', '').lower() - sign = +1 - if value[0] == '-': - sign = -1 - if value[0] in '+-': - value = value[1:] - if value == '.inf': - return sign*self.inf_value - elif value == '.nan': - return self.nan_value - elif ':' in value: - digits = [float(part) for part in value.split(':')] - digits.reverse() - base = 1 - value = 0.0 - for digit in digits: - value += digit*base - base *= 60 - return sign*value - else: - return sign*float(value) - - def construct_yaml_binary(self, node): - try: - value = self.construct_scalar(node).encode('ascii') - except UnicodeEncodeError as exc: - raise ConstructorError(None, None, - "failed to convert base64 data into ascii: %s" % exc, - node.start_mark) - try: - if hasattr(base64, 'decodebytes'): - return base64.decodebytes(value) - else: - return base64.decodestring(value) - except binascii.Error as exc: - raise ConstructorError(None, None, - "failed to decode base64 data: %s" % exc, node.start_mark) - - timestamp_regexp = re.compile( - r'''^(?P[0-9][0-9][0-9][0-9]) - -(?P[0-9][0-9]?) - -(?P[0-9][0-9]?) - (?:(?:[Tt]|[ \t]+) - (?P[0-9][0-9]?) - :(?P[0-9][0-9]) - :(?P[0-9][0-9]) - (?:\.(?P[0-9]*))? - (?:[ \t]*(?PZ|(?P[-+])(?P[0-9][0-9]?) - (?::(?P[0-9][0-9]))?))?)?$''', re.X) - - def construct_yaml_timestamp(self, node): - value = self.construct_scalar(node) - match = self.timestamp_regexp.match(node.value) - values = match.groupdict() - year = int(values['year']) - month = int(values['month']) - day = int(values['day']) - if not values['hour']: - return datetime.date(year, month, day) - hour = int(values['hour']) - minute = int(values['minute']) - second = int(values['second']) - fraction = 0 - tzinfo = None - if values['fraction']: - fraction = values['fraction'][:6] - while len(fraction) < 6: - fraction += '0' - fraction = int(fraction) - if values['tz_sign']: - tz_hour = int(values['tz_hour']) - tz_minute = int(values['tz_minute'] or 0) - delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute) - if values['tz_sign'] == '-': - delta = -delta - tzinfo = datetime.timezone(delta) - elif values['tz']: - tzinfo = datetime.timezone.utc - return datetime.datetime(year, month, day, hour, minute, second, fraction, - tzinfo=tzinfo) - - def construct_yaml_omap(self, node): - # Note: we do not check for duplicate keys, because it's too - # CPU-expensive. - omap = [] - yield omap - if not isinstance(node, SequenceNode): - raise ConstructorError("while constructing an ordered map", node.start_mark, - "expected a sequence, but found %s" % node.id, node.start_mark) - for subnode in node.value: - if not isinstance(subnode, MappingNode): - raise ConstructorError("while constructing an ordered map", node.start_mark, - "expected a mapping of length 1, but found %s" % subnode.id, - subnode.start_mark) - if len(subnode.value) != 1: - raise ConstructorError("while constructing an ordered map", node.start_mark, - "expected a single mapping item, but found %d items" % len(subnode.value), - subnode.start_mark) - key_node, value_node = subnode.value[0] - key = self.construct_object(key_node) - value = self.construct_object(value_node) - omap.append((key, value)) - - def construct_yaml_pairs(self, node): - # Note: the same code as `construct_yaml_omap`. - pairs = [] - yield pairs - if not isinstance(node, SequenceNode): - raise ConstructorError("while constructing pairs", node.start_mark, - "expected a sequence, but found %s" % node.id, node.start_mark) - for subnode in node.value: - if not isinstance(subnode, MappingNode): - raise ConstructorError("while constructing pairs", node.start_mark, - "expected a mapping of length 1, but found %s" % subnode.id, - subnode.start_mark) - if len(subnode.value) != 1: - raise ConstructorError("while constructing pairs", node.start_mark, - "expected a single mapping item, but found %d items" % len(subnode.value), - subnode.start_mark) - key_node, value_node = subnode.value[0] - key = self.construct_object(key_node) - value = self.construct_object(value_node) - pairs.append((key, value)) - - def construct_yaml_set(self, node): - data = set() - yield data - value = self.construct_mapping(node) - data.update(value) - - def construct_yaml_str(self, node): - return self.construct_scalar(node) - - def construct_yaml_seq(self, node): - data = [] - yield data - data.extend(self.construct_sequence(node)) - - def construct_yaml_map(self, node): - data = {} - yield data - value = self.construct_mapping(node) - data.update(value) - - def construct_yaml_object(self, node, cls): - data = cls.__new__(cls) - yield data - if hasattr(data, '__setstate__'): - state = self.construct_mapping(node, deep=True) - data.__setstate__(state) - else: - state = self.construct_mapping(node) - data.__dict__.update(state) - - def construct_undefined(self, node): - raise ConstructorError(None, None, - "could not determine a constructor for the tag %r" % node.tag, - node.start_mark) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:null', - SafeConstructor.construct_yaml_null) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:bool', - SafeConstructor.construct_yaml_bool) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:int', - SafeConstructor.construct_yaml_int) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:float', - SafeConstructor.construct_yaml_float) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:binary', - SafeConstructor.construct_yaml_binary) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:timestamp', - SafeConstructor.construct_yaml_timestamp) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:omap', - SafeConstructor.construct_yaml_omap) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:pairs', - SafeConstructor.construct_yaml_pairs) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:set', - SafeConstructor.construct_yaml_set) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:str', - SafeConstructor.construct_yaml_str) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:seq', - SafeConstructor.construct_yaml_seq) - -SafeConstructor.add_constructor( - 'tag:yaml.org,2002:map', - SafeConstructor.construct_yaml_map) - -SafeConstructor.add_constructor(None, - SafeConstructor.construct_undefined) - -class FullConstructor(SafeConstructor): - # 'extend' is blacklisted because it is used by - # construct_python_object_apply to add `listitems` to a newly generate - # python instance - def get_state_keys_blacklist(self): - return ['^extend$', '^__.*__$'] - - def get_state_keys_blacklist_regexp(self): - if not hasattr(self, 'state_keys_blacklist_regexp'): - self.state_keys_blacklist_regexp = re.compile('(' + '|'.join(self.get_state_keys_blacklist()) + ')') - return self.state_keys_blacklist_regexp - - def construct_python_str(self, node): - return self.construct_scalar(node) - - def construct_python_unicode(self, node): - return self.construct_scalar(node) - - def construct_python_bytes(self, node): - try: - value = self.construct_scalar(node).encode('ascii') - except UnicodeEncodeError as exc: - raise ConstructorError(None, None, - "failed to convert base64 data into ascii: %s" % exc, - node.start_mark) - try: - if hasattr(base64, 'decodebytes'): - return base64.decodebytes(value) - else: - return base64.decodestring(value) - except binascii.Error as exc: - raise ConstructorError(None, None, - "failed to decode base64 data: %s" % exc, node.start_mark) - - def construct_python_long(self, node): - return self.construct_yaml_int(node) - - def construct_python_complex(self, node): - return complex(self.construct_scalar(node)) - - def construct_python_tuple(self, node): - return tuple(self.construct_sequence(node)) - - def find_python_module(self, name, mark, unsafe=False): - if not name: - raise ConstructorError("while constructing a Python module", mark, - "expected non-empty name appended to the tag", mark) - if unsafe: - try: - __import__(name) - except ImportError as exc: - raise ConstructorError("while constructing a Python module", mark, - "cannot find module %r (%s)" % (name, exc), mark) - if name not in sys.modules: - raise ConstructorError("while constructing a Python module", mark, - "module %r is not imported" % name, mark) - return sys.modules[name] - - def find_python_name(self, name, mark, unsafe=False): - if not name: - raise ConstructorError("while constructing a Python object", mark, - "expected non-empty name appended to the tag", mark) - if '.' in name: - module_name, object_name = name.rsplit('.', 1) - else: - module_name = 'builtins' - object_name = name - if unsafe: - try: - __import__(module_name) - except ImportError as exc: - raise ConstructorError("while constructing a Python object", mark, - "cannot find module %r (%s)" % (module_name, exc), mark) - if module_name not in sys.modules: - raise ConstructorError("while constructing a Python object", mark, - "module %r is not imported" % module_name, mark) - module = sys.modules[module_name] - if not hasattr(module, object_name): - raise ConstructorError("while constructing a Python object", mark, - "cannot find %r in the module %r" - % (object_name, module.__name__), mark) - return getattr(module, object_name) - - def construct_python_name(self, suffix, node): - value = self.construct_scalar(node) - if value: - raise ConstructorError("while constructing a Python name", node.start_mark, - "expected the empty value, but found %r" % value, node.start_mark) - return self.find_python_name(suffix, node.start_mark) - - def construct_python_module(self, suffix, node): - value = self.construct_scalar(node) - if value: - raise ConstructorError("while constructing a Python module", node.start_mark, - "expected the empty value, but found %r" % value, node.start_mark) - return self.find_python_module(suffix, node.start_mark) - - def make_python_instance(self, suffix, node, - args=None, kwds=None, newobj=False, unsafe=False): - if not args: - args = [] - if not kwds: - kwds = {} - cls = self.find_python_name(suffix, node.start_mark) - if not (unsafe or isinstance(cls, type)): - raise ConstructorError("while constructing a Python instance", node.start_mark, - "expected a class, but found %r" % type(cls), - node.start_mark) - if newobj and isinstance(cls, type): - return cls.__new__(cls, *args, **kwds) - else: - return cls(*args, **kwds) - - def set_python_instance_state(self, instance, state, unsafe=False): - if hasattr(instance, '__setstate__'): - instance.__setstate__(state) - else: - slotstate = {} - if isinstance(state, tuple) and len(state) == 2: - state, slotstate = state - if hasattr(instance, '__dict__'): - if not unsafe and state: - for key in state.keys(): - self.check_state_key(key) - instance.__dict__.update(state) - elif state: - slotstate.update(state) - for key, value in slotstate.items(): - if not unsafe: - self.check_state_key(key) - setattr(instance, key, value) - - def construct_python_object(self, suffix, node): - # Format: - # !!python/object:module.name { ... state ... } - instance = self.make_python_instance(suffix, node, newobj=True) - yield instance - deep = hasattr(instance, '__setstate__') - state = self.construct_mapping(node, deep=deep) - self.set_python_instance_state(instance, state) - - def construct_python_object_apply(self, suffix, node, newobj=False): - # Format: - # !!python/object/apply # (or !!python/object/new) - # args: [ ... arguments ... ] - # kwds: { ... keywords ... } - # state: ... state ... - # listitems: [ ... listitems ... ] - # dictitems: { ... dictitems ... } - # or short format: - # !!python/object/apply [ ... arguments ... ] - # The difference between !!python/object/apply and !!python/object/new - # is how an object is created, check make_python_instance for details. - if isinstance(node, SequenceNode): - args = self.construct_sequence(node, deep=True) - kwds = {} - state = {} - listitems = [] - dictitems = {} - else: - value = self.construct_mapping(node, deep=True) - args = value.get('args', []) - kwds = value.get('kwds', {}) - state = value.get('state', {}) - listitems = value.get('listitems', []) - dictitems = value.get('dictitems', {}) - instance = self.make_python_instance(suffix, node, args, kwds, newobj) - if state: - self.set_python_instance_state(instance, state) - if listitems: - instance.extend(listitems) - if dictitems: - for key in dictitems: - instance[key] = dictitems[key] - return instance - - def construct_python_object_new(self, suffix, node): - return self.construct_python_object_apply(suffix, node, newobj=True) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/none', - FullConstructor.construct_yaml_null) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/bool', - FullConstructor.construct_yaml_bool) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/str', - FullConstructor.construct_python_str) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/unicode', - FullConstructor.construct_python_unicode) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/bytes', - FullConstructor.construct_python_bytes) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/int', - FullConstructor.construct_yaml_int) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/long', - FullConstructor.construct_python_long) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/float', - FullConstructor.construct_yaml_float) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/complex', - FullConstructor.construct_python_complex) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/list', - FullConstructor.construct_yaml_seq) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/tuple', - FullConstructor.construct_python_tuple) - -FullConstructor.add_constructor( - 'tag:yaml.org,2002:python/dict', - FullConstructor.construct_yaml_map) - -FullConstructor.add_multi_constructor( - 'tag:yaml.org,2002:python/name:', - FullConstructor.construct_python_name) - -FullConstructor.add_multi_constructor( - 'tag:yaml.org,2002:python/module:', - FullConstructor.construct_python_module) - -FullConstructor.add_multi_constructor( - 'tag:yaml.org,2002:python/object:', - FullConstructor.construct_python_object) - -FullConstructor.add_multi_constructor( - 'tag:yaml.org,2002:python/object/new:', - FullConstructor.construct_python_object_new) - -class UnsafeConstructor(FullConstructor): - - def find_python_module(self, name, mark): - return super(UnsafeConstructor, self).find_python_module(name, mark, unsafe=True) - - def find_python_name(self, name, mark): - return super(UnsafeConstructor, self).find_python_name(name, mark, unsafe=True) - - def make_python_instance(self, suffix, node, args=None, kwds=None, newobj=False): - return super(UnsafeConstructor, self).make_python_instance( - suffix, node, args, kwds, newobj, unsafe=True) - - def set_python_instance_state(self, instance, state): - return super(UnsafeConstructor, self).set_python_instance_state( - instance, state, unsafe=True) - -UnsafeConstructor.add_multi_constructor( - 'tag:yaml.org,2002:python/object/apply:', - UnsafeConstructor.construct_python_object_apply) - -# Constructor is same as UnsafeConstructor. Need to leave this in place in case -# people have extended it directly. -class Constructor(UnsafeConstructor): - pass diff --git a/src/yaml/cyaml.py b/src/yaml/cyaml.py deleted file mode 100644 index 1e606c7..0000000 --- a/src/yaml/cyaml.py +++ /dev/null @@ -1,101 +0,0 @@ - -__all__ = [ - 'CBaseLoader', 'CSafeLoader', 'CFullLoader', 'CUnsafeLoader', 'CLoader', - 'CBaseDumper', 'CSafeDumper', 'CDumper' -] - -from _yaml import CParser, CEmitter - -from .constructor import * - -from .serializer import * -from .representer import * - -from .resolver import * - -class CBaseLoader(CParser, BaseConstructor, BaseResolver): - - def __init__(self, stream): - CParser.__init__(self, stream) - BaseConstructor.__init__(self) - BaseResolver.__init__(self) - -class CSafeLoader(CParser, SafeConstructor, Resolver): - - def __init__(self, stream): - CParser.__init__(self, stream) - SafeConstructor.__init__(self) - Resolver.__init__(self) - -class CFullLoader(CParser, FullConstructor, Resolver): - - def __init__(self, stream): - CParser.__init__(self, stream) - FullConstructor.__init__(self) - Resolver.__init__(self) - -class CUnsafeLoader(CParser, UnsafeConstructor, Resolver): - - def __init__(self, stream): - CParser.__init__(self, stream) - UnsafeConstructor.__init__(self) - Resolver.__init__(self) - -class CLoader(CParser, Constructor, Resolver): - - def __init__(self, stream): - CParser.__init__(self, stream) - Constructor.__init__(self) - Resolver.__init__(self) - -class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver): - - def __init__(self, stream, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - CEmitter.__init__(self, stream, canonical=canonical, - indent=indent, width=width, encoding=encoding, - allow_unicode=allow_unicode, line_break=line_break, - explicit_start=explicit_start, explicit_end=explicit_end, - version=version, tags=tags) - Representer.__init__(self, default_style=default_style, - default_flow_style=default_flow_style, sort_keys=sort_keys) - Resolver.__init__(self) - -class CSafeDumper(CEmitter, SafeRepresenter, Resolver): - - def __init__(self, stream, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - CEmitter.__init__(self, stream, canonical=canonical, - indent=indent, width=width, encoding=encoding, - allow_unicode=allow_unicode, line_break=line_break, - explicit_start=explicit_start, explicit_end=explicit_end, - version=version, tags=tags) - SafeRepresenter.__init__(self, default_style=default_style, - default_flow_style=default_flow_style, sort_keys=sort_keys) - Resolver.__init__(self) - -class CDumper(CEmitter, Serializer, Representer, Resolver): - - def __init__(self, stream, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - CEmitter.__init__(self, stream, canonical=canonical, - indent=indent, width=width, encoding=encoding, - allow_unicode=allow_unicode, line_break=line_break, - explicit_start=explicit_start, explicit_end=explicit_end, - version=version, tags=tags) - Representer.__init__(self, default_style=default_style, - default_flow_style=default_flow_style, sort_keys=sort_keys) - Resolver.__init__(self) - diff --git a/src/yaml/dumper.py b/src/yaml/dumper.py deleted file mode 100644 index 6aadba5..0000000 --- a/src/yaml/dumper.py +++ /dev/null @@ -1,62 +0,0 @@ - -__all__ = ['BaseDumper', 'SafeDumper', 'Dumper'] - -from .emitter import * -from .serializer import * -from .representer import * -from .resolver import * - -class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver): - - def __init__(self, stream, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - Emitter.__init__(self, stream, canonical=canonical, - indent=indent, width=width, - allow_unicode=allow_unicode, line_break=line_break) - Serializer.__init__(self, encoding=encoding, - explicit_start=explicit_start, explicit_end=explicit_end, - version=version, tags=tags) - Representer.__init__(self, default_style=default_style, - default_flow_style=default_flow_style, sort_keys=sort_keys) - Resolver.__init__(self) - -class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver): - - def __init__(self, stream, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - Emitter.__init__(self, stream, canonical=canonical, - indent=indent, width=width, - allow_unicode=allow_unicode, line_break=line_break) - Serializer.__init__(self, encoding=encoding, - explicit_start=explicit_start, explicit_end=explicit_end, - version=version, tags=tags) - SafeRepresenter.__init__(self, default_style=default_style, - default_flow_style=default_flow_style, sort_keys=sort_keys) - Resolver.__init__(self) - -class Dumper(Emitter, Serializer, Representer, Resolver): - - def __init__(self, stream, - default_style=None, default_flow_style=False, - canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None, - encoding=None, explicit_start=None, explicit_end=None, - version=None, tags=None, sort_keys=True): - Emitter.__init__(self, stream, canonical=canonical, - indent=indent, width=width, - allow_unicode=allow_unicode, line_break=line_break) - Serializer.__init__(self, encoding=encoding, - explicit_start=explicit_start, explicit_end=explicit_end, - version=version, tags=tags) - Representer.__init__(self, default_style=default_style, - default_flow_style=default_flow_style, sort_keys=sort_keys) - Resolver.__init__(self) - diff --git a/src/yaml/emitter.py b/src/yaml/emitter.py deleted file mode 100644 index a664d01..0000000 --- a/src/yaml/emitter.py +++ /dev/null @@ -1,1137 +0,0 @@ - -# Emitter expects events obeying the following grammar: -# stream ::= STREAM-START document* STREAM-END -# document ::= DOCUMENT-START node DOCUMENT-END -# node ::= SCALAR | sequence | mapping -# sequence ::= SEQUENCE-START node* SEQUENCE-END -# mapping ::= MAPPING-START (node node)* MAPPING-END - -__all__ = ['Emitter', 'EmitterError'] - -from .error import YAMLError -from .events import * - -class EmitterError(YAMLError): - pass - -class ScalarAnalysis: - def __init__(self, scalar, empty, multiline, - allow_flow_plain, allow_block_plain, - allow_single_quoted, allow_double_quoted, - allow_block): - self.scalar = scalar - self.empty = empty - self.multiline = multiline - self.allow_flow_plain = allow_flow_plain - self.allow_block_plain = allow_block_plain - self.allow_single_quoted = allow_single_quoted - self.allow_double_quoted = allow_double_quoted - self.allow_block = allow_block - -class Emitter: - - DEFAULT_TAG_PREFIXES = { - '!' : '!', - 'tag:yaml.org,2002:' : '!!', - } - - def __init__(self, stream, canonical=None, indent=None, width=None, - allow_unicode=None, line_break=None): - - # The stream should have the methods `write` and possibly `flush`. - self.stream = stream - - # Encoding can be overridden by STREAM-START. - self.encoding = None - - # Emitter is a state machine with a stack of states to handle nested - # structures. - self.states = [] - self.state = self.expect_stream_start - - # Current event and the event queue. - self.events = [] - self.event = None - - # The current indentation level and the stack of previous indents. - self.indents = [] - self.indent = None - - # Flow level. - self.flow_level = 0 - - # Contexts. - self.root_context = False - self.sequence_context = False - self.mapping_context = False - self.simple_key_context = False - - # Characteristics of the last emitted character: - # - current position. - # - is it a whitespace? - # - is it an indention character - # (indentation space, '-', '?', or ':')? - self.line = 0 - self.column = 0 - self.whitespace = True - self.indention = True - - # Whether the document requires an explicit document indicator - self.open_ended = False - - # Formatting details. - self.canonical = canonical - self.allow_unicode = allow_unicode - self.best_indent = 2 - if indent and 1 < indent < 10: - self.best_indent = indent - self.best_width = 80 - if width and width > self.best_indent*2: - self.best_width = width - self.best_line_break = '\n' - if line_break in ['\r', '\n', '\r\n']: - self.best_line_break = line_break - - # Tag prefixes. - self.tag_prefixes = None - - # Prepared anchor and tag. - self.prepared_anchor = None - self.prepared_tag = None - - # Scalar analysis and style. - self.analysis = None - self.style = None - - def dispose(self): - # Reset the state attributes (to clear self-references) - self.states = [] - self.state = None - - def emit(self, event): - self.events.append(event) - while not self.need_more_events(): - self.event = self.events.pop(0) - self.state() - self.event = None - - # In some cases, we wait for a few next events before emitting. - - def need_more_events(self): - if not self.events: - return True - event = self.events[0] - if isinstance(event, DocumentStartEvent): - return self.need_events(1) - elif isinstance(event, SequenceStartEvent): - return self.need_events(2) - elif isinstance(event, MappingStartEvent): - return self.need_events(3) - else: - return False - - def need_events(self, count): - level = 0 - for event in self.events[1:]: - if isinstance(event, (DocumentStartEvent, CollectionStartEvent)): - level += 1 - elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)): - level -= 1 - elif isinstance(event, StreamEndEvent): - level = -1 - if level < 0: - return False - return (len(self.events) < count+1) - - def increase_indent(self, flow=False, indentless=False): - self.indents.append(self.indent) - if self.indent is None: - if flow: - self.indent = self.best_indent - else: - self.indent = 0 - elif not indentless: - self.indent += self.best_indent - - # States. - - # Stream handlers. - - def expect_stream_start(self): - if isinstance(self.event, StreamStartEvent): - if self.event.encoding and not hasattr(self.stream, 'encoding'): - self.encoding = self.event.encoding - self.write_stream_start() - self.state = self.expect_first_document_start - else: - raise EmitterError("expected StreamStartEvent, but got %s" - % self.event) - - def expect_nothing(self): - raise EmitterError("expected nothing, but got %s" % self.event) - - # Document handlers. - - def expect_first_document_start(self): - return self.expect_document_start(first=True) - - def expect_document_start(self, first=False): - if isinstance(self.event, DocumentStartEvent): - if (self.event.version or self.event.tags) and self.open_ended: - self.write_indicator('...', True) - self.write_indent() - if self.event.version: - version_text = self.prepare_version(self.event.version) - self.write_version_directive(version_text) - self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy() - if self.event.tags: - handles = sorted(self.event.tags.keys()) - for handle in handles: - prefix = self.event.tags[handle] - self.tag_prefixes[prefix] = handle - handle_text = self.prepare_tag_handle(handle) - prefix_text = self.prepare_tag_prefix(prefix) - self.write_tag_directive(handle_text, prefix_text) - implicit = (first and not self.event.explicit and not self.canonical - and not self.event.version and not self.event.tags - and not self.check_empty_document()) - if not implicit: - self.write_indent() - self.write_indicator('---', True) - if self.canonical: - self.write_indent() - self.state = self.expect_document_root - elif isinstance(self.event, StreamEndEvent): - if self.open_ended: - self.write_indicator('...', True) - self.write_indent() - self.write_stream_end() - self.state = self.expect_nothing - else: - raise EmitterError("expected DocumentStartEvent, but got %s" - % self.event) - - def expect_document_end(self): - if isinstance(self.event, DocumentEndEvent): - self.write_indent() - if self.event.explicit: - self.write_indicator('...', True) - self.write_indent() - self.flush_stream() - self.state = self.expect_document_start - else: - raise EmitterError("expected DocumentEndEvent, but got %s" - % self.event) - - def expect_document_root(self): - self.states.append(self.expect_document_end) - self.expect_node(root=True) - - # Node handlers. - - def expect_node(self, root=False, sequence=False, mapping=False, - simple_key=False): - self.root_context = root - self.sequence_context = sequence - self.mapping_context = mapping - self.simple_key_context = simple_key - if isinstance(self.event, AliasEvent): - self.expect_alias() - elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)): - self.process_anchor('&') - self.process_tag() - if isinstance(self.event, ScalarEvent): - self.expect_scalar() - elif isinstance(self.event, SequenceStartEvent): - if self.flow_level or self.canonical or self.event.flow_style \ - or self.check_empty_sequence(): - self.expect_flow_sequence() - else: - self.expect_block_sequence() - elif isinstance(self.event, MappingStartEvent): - if self.flow_level or self.canonical or self.event.flow_style \ - or self.check_empty_mapping(): - self.expect_flow_mapping() - else: - self.expect_block_mapping() - else: - raise EmitterError("expected NodeEvent, but got %s" % self.event) - - def expect_alias(self): - if self.event.anchor is None: - raise EmitterError("anchor is not specified for alias") - self.process_anchor('*') - self.state = self.states.pop() - - def expect_scalar(self): - self.increase_indent(flow=True) - self.process_scalar() - self.indent = self.indents.pop() - self.state = self.states.pop() - - # Flow sequence handlers. - - def expect_flow_sequence(self): - self.write_indicator('[', True, whitespace=True) - self.flow_level += 1 - self.increase_indent(flow=True) - self.state = self.expect_first_flow_sequence_item - - def expect_first_flow_sequence_item(self): - if isinstance(self.event, SequenceEndEvent): - self.indent = self.indents.pop() - self.flow_level -= 1 - self.write_indicator(']', False) - self.state = self.states.pop() - else: - if self.canonical or self.column > self.best_width: - self.write_indent() - self.states.append(self.expect_flow_sequence_item) - self.expect_node(sequence=True) - - def expect_flow_sequence_item(self): - if isinstance(self.event, SequenceEndEvent): - self.indent = self.indents.pop() - self.flow_level -= 1 - if self.canonical: - self.write_indicator(',', False) - self.write_indent() - self.write_indicator(']', False) - self.state = self.states.pop() - else: - self.write_indicator(',', False) - if self.canonical or self.column > self.best_width: - self.write_indent() - self.states.append(self.expect_flow_sequence_item) - self.expect_node(sequence=True) - - # Flow mapping handlers. - - def expect_flow_mapping(self): - self.write_indicator('{', True, whitespace=True) - self.flow_level += 1 - self.increase_indent(flow=True) - self.state = self.expect_first_flow_mapping_key - - def expect_first_flow_mapping_key(self): - if isinstance(self.event, MappingEndEvent): - self.indent = self.indents.pop() - self.flow_level -= 1 - self.write_indicator('}', False) - self.state = self.states.pop() - else: - if self.canonical or self.column > self.best_width: - self.write_indent() - if not self.canonical and self.check_simple_key(): - self.states.append(self.expect_flow_mapping_simple_value) - self.expect_node(mapping=True, simple_key=True) - else: - self.write_indicator('?', True) - self.states.append(self.expect_flow_mapping_value) - self.expect_node(mapping=True) - - def expect_flow_mapping_key(self): - if isinstance(self.event, MappingEndEvent): - self.indent = self.indents.pop() - self.flow_level -= 1 - if self.canonical: - self.write_indicator(',', False) - self.write_indent() - self.write_indicator('}', False) - self.state = self.states.pop() - else: - self.write_indicator(',', False) - if self.canonical or self.column > self.best_width: - self.write_indent() - if not self.canonical and self.check_simple_key(): - self.states.append(self.expect_flow_mapping_simple_value) - self.expect_node(mapping=True, simple_key=True) - else: - self.write_indicator('?', True) - self.states.append(self.expect_flow_mapping_value) - self.expect_node(mapping=True) - - def expect_flow_mapping_simple_value(self): - self.write_indicator(':', False) - self.states.append(self.expect_flow_mapping_key) - self.expect_node(mapping=True) - - def expect_flow_mapping_value(self): - if self.canonical or self.column > self.best_width: - self.write_indent() - self.write_indicator(':', True) - self.states.append(self.expect_flow_mapping_key) - self.expect_node(mapping=True) - - # Block sequence handlers. - - def expect_block_sequence(self): - indentless = (self.mapping_context and not self.indention) - self.increase_indent(flow=False, indentless=indentless) - self.state = self.expect_first_block_sequence_item - - def expect_first_block_sequence_item(self): - return self.expect_block_sequence_item(first=True) - - def expect_block_sequence_item(self, first=False): - if not first and isinstance(self.event, SequenceEndEvent): - self.indent = self.indents.pop() - self.state = self.states.pop() - else: - self.write_indent() - self.write_indicator('-', True, indention=True) - self.states.append(self.expect_block_sequence_item) - self.expect_node(sequence=True) - - # Block mapping handlers. - - def expect_block_mapping(self): - self.increase_indent(flow=False) - self.state = self.expect_first_block_mapping_key - - def expect_first_block_mapping_key(self): - return self.expect_block_mapping_key(first=True) - - def expect_block_mapping_key(self, first=False): - if not first and isinstance(self.event, MappingEndEvent): - self.indent = self.indents.pop() - self.state = self.states.pop() - else: - self.write_indent() - if self.check_simple_key(): - self.states.append(self.expect_block_mapping_simple_value) - self.expect_node(mapping=True, simple_key=True) - else: - self.write_indicator('?', True, indention=True) - self.states.append(self.expect_block_mapping_value) - self.expect_node(mapping=True) - - def expect_block_mapping_simple_value(self): - self.write_indicator(':', False) - self.states.append(self.expect_block_mapping_key) - self.expect_node(mapping=True) - - def expect_block_mapping_value(self): - self.write_indent() - self.write_indicator(':', True, indention=True) - self.states.append(self.expect_block_mapping_key) - self.expect_node(mapping=True) - - # Checkers. - - def check_empty_sequence(self): - return (isinstance(self.event, SequenceStartEvent) and self.events - and isinstance(self.events[0], SequenceEndEvent)) - - def check_empty_mapping(self): - return (isinstance(self.event, MappingStartEvent) and self.events - and isinstance(self.events[0], MappingEndEvent)) - - def check_empty_document(self): - if not isinstance(self.event, DocumentStartEvent) or not self.events: - return False - event = self.events[0] - return (isinstance(event, ScalarEvent) and event.anchor is None - and event.tag is None and event.implicit and event.value == '') - - def check_simple_key(self): - length = 0 - if isinstance(self.event, NodeEvent) and self.event.anchor is not None: - if self.prepared_anchor is None: - self.prepared_anchor = self.prepare_anchor(self.event.anchor) - length += len(self.prepared_anchor) - if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \ - and self.event.tag is not None: - if self.prepared_tag is None: - self.prepared_tag = self.prepare_tag(self.event.tag) - length += len(self.prepared_tag) - if isinstance(self.event, ScalarEvent): - if self.analysis is None: - self.analysis = self.analyze_scalar(self.event.value) - length += len(self.analysis.scalar) - return (length < 128 and (isinstance(self.event, AliasEvent) - or (isinstance(self.event, ScalarEvent) - and not self.analysis.empty and not self.analysis.multiline) - or self.check_empty_sequence() or self.check_empty_mapping())) - - # Anchor, Tag, and Scalar processors. - - def process_anchor(self, indicator): - if self.event.anchor is None: - self.prepared_anchor = None - return - if self.prepared_anchor is None: - self.prepared_anchor = self.prepare_anchor(self.event.anchor) - if self.prepared_anchor: - self.write_indicator(indicator+self.prepared_anchor, True) - self.prepared_anchor = None - - def process_tag(self): - tag = self.event.tag - if isinstance(self.event, ScalarEvent): - if self.style is None: - self.style = self.choose_scalar_style() - if ((not self.canonical or tag is None) and - ((self.style == '' and self.event.implicit[0]) - or (self.style != '' and self.event.implicit[1]))): - self.prepared_tag = None - return - if self.event.implicit[0] and tag is None: - tag = '!' - self.prepared_tag = None - else: - if (not self.canonical or tag is None) and self.event.implicit: - self.prepared_tag = None - return - if tag is None: - raise EmitterError("tag is not specified") - if self.prepared_tag is None: - self.prepared_tag = self.prepare_tag(tag) - if self.prepared_tag: - self.write_indicator(self.prepared_tag, True) - self.prepared_tag = None - - def choose_scalar_style(self): - if self.analysis is None: - self.analysis = self.analyze_scalar(self.event.value) - if self.event.style == '"' or self.canonical: - return '"' - if not self.event.style and self.event.implicit[0]: - if (not (self.simple_key_context and - (self.analysis.empty or self.analysis.multiline)) - and (self.flow_level and self.analysis.allow_flow_plain - or (not self.flow_level and self.analysis.allow_block_plain))): - return '' - if self.event.style and self.event.style in '|>': - if (not self.flow_level and not self.simple_key_context - and self.analysis.allow_block): - return self.event.style - if not self.event.style or self.event.style == '\'': - if (self.analysis.allow_single_quoted and - not (self.simple_key_context and self.analysis.multiline)): - return '\'' - return '"' - - def process_scalar(self): - if self.analysis is None: - self.analysis = self.analyze_scalar(self.event.value) - if self.style is None: - self.style = self.choose_scalar_style() - split = (not self.simple_key_context) - #if self.analysis.multiline and split \ - # and (not self.style or self.style in '\'\"'): - # self.write_indent() - if self.style == '"': - self.write_double_quoted(self.analysis.scalar, split) - elif self.style == '\'': - self.write_single_quoted(self.analysis.scalar, split) - elif self.style == '>': - self.write_folded(self.analysis.scalar) - elif self.style == '|': - self.write_literal(self.analysis.scalar) - else: - self.write_plain(self.analysis.scalar, split) - self.analysis = None - self.style = None - - # Analyzers. - - def prepare_version(self, version): - major, minor = version - if major != 1: - raise EmitterError("unsupported YAML version: %d.%d" % (major, minor)) - return '%d.%d' % (major, minor) - - def prepare_tag_handle(self, handle): - if not handle: - raise EmitterError("tag handle must not be empty") - if handle[0] != '!' or handle[-1] != '!': - raise EmitterError("tag handle must start and end with '!': %r" % handle) - for ch in handle[1:-1]: - if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-_'): - raise EmitterError("invalid character %r in the tag handle: %r" - % (ch, handle)) - return handle - - def prepare_tag_prefix(self, prefix): - if not prefix: - raise EmitterError("tag prefix must not be empty") - chunks = [] - start = end = 0 - if prefix[0] == '!': - end = 1 - while end < len(prefix): - ch = prefix[end] - if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-;/?!:@&=+$,_.~*\'()[]': - end += 1 - else: - if start < end: - chunks.append(prefix[start:end]) - start = end = end+1 - data = ch.encode('utf-8') - for ch in data: - chunks.append('%%%02X' % ord(ch)) - if start < end: - chunks.append(prefix[start:end]) - return ''.join(chunks) - - def prepare_tag(self, tag): - if not tag: - raise EmitterError("tag must not be empty") - if tag == '!': - return tag - handle = None - suffix = tag - prefixes = sorted(self.tag_prefixes.keys()) - for prefix in prefixes: - if tag.startswith(prefix) \ - and (prefix == '!' or len(prefix) < len(tag)): - handle = self.tag_prefixes[prefix] - suffix = tag[len(prefix):] - chunks = [] - start = end = 0 - while end < len(suffix): - ch = suffix[end] - if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-;/?:@&=+$,_.~*\'()[]' \ - or (ch == '!' and handle != '!'): - end += 1 - else: - if start < end: - chunks.append(suffix[start:end]) - start = end = end+1 - data = ch.encode('utf-8') - for ch in data: - chunks.append('%%%02X' % ch) - if start < end: - chunks.append(suffix[start:end]) - suffix_text = ''.join(chunks) - if handle: - return '%s%s' % (handle, suffix_text) - else: - return '!<%s>' % suffix_text - - def prepare_anchor(self, anchor): - if not anchor: - raise EmitterError("anchor must not be empty") - for ch in anchor: - if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-_'): - raise EmitterError("invalid character %r in the anchor: %r" - % (ch, anchor)) - return anchor - - def analyze_scalar(self, scalar): - - # Empty scalar is a special case. - if not scalar: - return ScalarAnalysis(scalar=scalar, empty=True, multiline=False, - allow_flow_plain=False, allow_block_plain=True, - allow_single_quoted=True, allow_double_quoted=True, - allow_block=False) - - # Indicators and special characters. - block_indicators = False - flow_indicators = False - line_breaks = False - special_characters = False - - # Important whitespace combinations. - leading_space = False - leading_break = False - trailing_space = False - trailing_break = False - break_space = False - space_break = False - - # Check document indicators. - if scalar.startswith('---') or scalar.startswith('...'): - block_indicators = True - flow_indicators = True - - # First character or preceded by a whitespace. - preceded_by_whitespace = True - - # Last character or followed by a whitespace. - followed_by_whitespace = (len(scalar) == 1 or - scalar[1] in '\0 \t\r\n\x85\u2028\u2029') - - # The previous character is a space. - previous_space = False - - # The previous character is a break. - previous_break = False - - index = 0 - while index < len(scalar): - ch = scalar[index] - - # Check for indicators. - if index == 0: - # Leading indicators are special characters. - if ch in '#,[]{}&*!|>\'\"%@`': - flow_indicators = True - block_indicators = True - if ch in '?:': - flow_indicators = True - if followed_by_whitespace: - block_indicators = True - if ch == '-' and followed_by_whitespace: - flow_indicators = True - block_indicators = True - else: - # Some indicators cannot appear within a scalar as well. - if ch in ',?[]{}': - flow_indicators = True - if ch == ':': - flow_indicators = True - if followed_by_whitespace: - block_indicators = True - if ch == '#' and preceded_by_whitespace: - flow_indicators = True - block_indicators = True - - # Check for line breaks, special, and unicode characters. - if ch in '\n\x85\u2028\u2029': - line_breaks = True - if not (ch == '\n' or '\x20' <= ch <= '\x7E'): - if (ch == '\x85' or '\xA0' <= ch <= '\uD7FF' - or '\uE000' <= ch <= '\uFFFD' - or '\U00010000' <= ch < '\U0010ffff') and ch != '\uFEFF': - unicode_characters = True - if not self.allow_unicode: - special_characters = True - else: - special_characters = True - - # Detect important whitespace combinations. - if ch == ' ': - if index == 0: - leading_space = True - if index == len(scalar)-1: - trailing_space = True - if previous_break: - break_space = True - previous_space = True - previous_break = False - elif ch in '\n\x85\u2028\u2029': - if index == 0: - leading_break = True - if index == len(scalar)-1: - trailing_break = True - if previous_space: - space_break = True - previous_space = False - previous_break = True - else: - previous_space = False - previous_break = False - - # Prepare for the next character. - index += 1 - preceded_by_whitespace = (ch in '\0 \t\r\n\x85\u2028\u2029') - followed_by_whitespace = (index+1 >= len(scalar) or - scalar[index+1] in '\0 \t\r\n\x85\u2028\u2029') - - # Let's decide what styles are allowed. - allow_flow_plain = True - allow_block_plain = True - allow_single_quoted = True - allow_double_quoted = True - allow_block = True - - # Leading and trailing whitespaces are bad for plain scalars. - if (leading_space or leading_break - or trailing_space or trailing_break): - allow_flow_plain = allow_block_plain = False - - # We do not permit trailing spaces for block scalars. - if trailing_space: - allow_block = False - - # Spaces at the beginning of a new line are only acceptable for block - # scalars. - if break_space: - allow_flow_plain = allow_block_plain = allow_single_quoted = False - - # Spaces followed by breaks, as well as special character are only - # allowed for double quoted scalars. - if space_break or special_characters: - allow_flow_plain = allow_block_plain = \ - allow_single_quoted = allow_block = False - - # Although the plain scalar writer supports breaks, we never emit - # multiline plain scalars. - if line_breaks: - allow_flow_plain = allow_block_plain = False - - # Flow indicators are forbidden for flow plain scalars. - if flow_indicators: - allow_flow_plain = False - - # Block indicators are forbidden for block plain scalars. - if block_indicators: - allow_block_plain = False - - return ScalarAnalysis(scalar=scalar, - empty=False, multiline=line_breaks, - allow_flow_plain=allow_flow_plain, - allow_block_plain=allow_block_plain, - allow_single_quoted=allow_single_quoted, - allow_double_quoted=allow_double_quoted, - allow_block=allow_block) - - # Writers. - - def flush_stream(self): - if hasattr(self.stream, 'flush'): - self.stream.flush() - - def write_stream_start(self): - # Write BOM if needed. - if self.encoding and self.encoding.startswith('utf-16'): - self.stream.write('\uFEFF'.encode(self.encoding)) - - def write_stream_end(self): - self.flush_stream() - - def write_indicator(self, indicator, need_whitespace, - whitespace=False, indention=False): - if self.whitespace or not need_whitespace: - data = indicator - else: - data = ' '+indicator - self.whitespace = whitespace - self.indention = self.indention and indention - self.column += len(data) - self.open_ended = False - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - - def write_indent(self): - indent = self.indent or 0 - if not self.indention or self.column > indent \ - or (self.column == indent and not self.whitespace): - self.write_line_break() - if self.column < indent: - self.whitespace = True - data = ' '*(indent-self.column) - self.column = indent - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - - def write_line_break(self, data=None): - if data is None: - data = self.best_line_break - self.whitespace = True - self.indention = True - self.line += 1 - self.column = 0 - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - - def write_version_directive(self, version_text): - data = '%%YAML %s' % version_text - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - self.write_line_break() - - def write_tag_directive(self, handle_text, prefix_text): - data = '%%TAG %s %s' % (handle_text, prefix_text) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - self.write_line_break() - - # Scalar streams. - - def write_single_quoted(self, text, split=True): - self.write_indicator('\'', True) - spaces = False - breaks = False - start = end = 0 - while end <= len(text): - ch = None - if end < len(text): - ch = text[end] - if spaces: - if ch is None or ch != ' ': - if start+1 == end and self.column > self.best_width and split \ - and start != 0 and end != len(text): - self.write_indent() - else: - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end - elif breaks: - if ch is None or ch not in '\n\x85\u2028\u2029': - if text[start] == '\n': - self.write_line_break() - for br in text[start:end]: - if br == '\n': - self.write_line_break() - else: - self.write_line_break(br) - self.write_indent() - start = end - else: - if ch is None or ch in ' \n\x85\u2028\u2029' or ch == '\'': - if start < end: - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end - if ch == '\'': - data = '\'\'' - self.column += 2 - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end + 1 - if ch is not None: - spaces = (ch == ' ') - breaks = (ch in '\n\x85\u2028\u2029') - end += 1 - self.write_indicator('\'', False) - - ESCAPE_REPLACEMENTS = { - '\0': '0', - '\x07': 'a', - '\x08': 'b', - '\x09': 't', - '\x0A': 'n', - '\x0B': 'v', - '\x0C': 'f', - '\x0D': 'r', - '\x1B': 'e', - '\"': '\"', - '\\': '\\', - '\x85': 'N', - '\xA0': '_', - '\u2028': 'L', - '\u2029': 'P', - } - - def write_double_quoted(self, text, split=True): - self.write_indicator('"', True) - start = end = 0 - while end <= len(text): - ch = None - if end < len(text): - ch = text[end] - if ch is None or ch in '"\\\x85\u2028\u2029\uFEFF' \ - or not ('\x20' <= ch <= '\x7E' - or (self.allow_unicode - and ('\xA0' <= ch <= '\uD7FF' - or '\uE000' <= ch <= '\uFFFD'))): - if start < end: - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end - if ch is not None: - if ch in self.ESCAPE_REPLACEMENTS: - data = '\\'+self.ESCAPE_REPLACEMENTS[ch] - elif ch <= '\xFF': - data = '\\x%02X' % ord(ch) - elif ch <= '\uFFFF': - data = '\\u%04X' % ord(ch) - else: - data = '\\U%08X' % ord(ch) - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end+1 - if 0 < end < len(text)-1 and (ch == ' ' or start >= end) \ - and self.column+(end-start) > self.best_width and split: - data = text[start:end]+'\\' - if start < end: - start = end - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - self.write_indent() - self.whitespace = False - self.indention = False - if text[start] == ' ': - data = '\\' - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - end += 1 - self.write_indicator('"', False) - - def determine_block_hints(self, text): - hints = '' - if text: - if text[0] in ' \n\x85\u2028\u2029': - hints += str(self.best_indent) - if text[-1] not in '\n\x85\u2028\u2029': - hints += '-' - elif len(text) == 1 or text[-2] in '\n\x85\u2028\u2029': - hints += '+' - return hints - - def write_folded(self, text): - hints = self.determine_block_hints(text) - self.write_indicator('>'+hints, True) - if hints[-1:] == '+': - self.open_ended = True - self.write_line_break() - leading_space = True - spaces = False - breaks = True - start = end = 0 - while end <= len(text): - ch = None - if end < len(text): - ch = text[end] - if breaks: - if ch is None or ch not in '\n\x85\u2028\u2029': - if not leading_space and ch is not None and ch != ' ' \ - and text[start] == '\n': - self.write_line_break() - leading_space = (ch == ' ') - for br in text[start:end]: - if br == '\n': - self.write_line_break() - else: - self.write_line_break(br) - if ch is not None: - self.write_indent() - start = end - elif spaces: - if ch != ' ': - if start+1 == end and self.column > self.best_width: - self.write_indent() - else: - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end - else: - if ch is None or ch in ' \n\x85\u2028\u2029': - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - if ch is None: - self.write_line_break() - start = end - if ch is not None: - breaks = (ch in '\n\x85\u2028\u2029') - spaces = (ch == ' ') - end += 1 - - def write_literal(self, text): - hints = self.determine_block_hints(text) - self.write_indicator('|'+hints, True) - if hints[-1:] == '+': - self.open_ended = True - self.write_line_break() - breaks = True - start = end = 0 - while end <= len(text): - ch = None - if end < len(text): - ch = text[end] - if breaks: - if ch is None or ch not in '\n\x85\u2028\u2029': - for br in text[start:end]: - if br == '\n': - self.write_line_break() - else: - self.write_line_break(br) - if ch is not None: - self.write_indent() - start = end - else: - if ch is None or ch in '\n\x85\u2028\u2029': - data = text[start:end] - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - if ch is None: - self.write_line_break() - start = end - if ch is not None: - breaks = (ch in '\n\x85\u2028\u2029') - end += 1 - - def write_plain(self, text, split=True): - if self.root_context: - self.open_ended = True - if not text: - return - if not self.whitespace: - data = ' ' - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - self.whitespace = False - self.indention = False - spaces = False - breaks = False - start = end = 0 - while end <= len(text): - ch = None - if end < len(text): - ch = text[end] - if spaces: - if ch != ' ': - if start+1 == end and self.column > self.best_width and split: - self.write_indent() - self.whitespace = False - self.indention = False - else: - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end - elif breaks: - if ch not in '\n\x85\u2028\u2029': - if text[start] == '\n': - self.write_line_break() - for br in text[start:end]: - if br == '\n': - self.write_line_break() - else: - self.write_line_break(br) - self.write_indent() - self.whitespace = False - self.indention = False - start = end - else: - if ch is None or ch in ' \n\x85\u2028\u2029': - data = text[start:end] - self.column += len(data) - if self.encoding: - data = data.encode(self.encoding) - self.stream.write(data) - start = end - if ch is not None: - spaces = (ch == ' ') - breaks = (ch in '\n\x85\u2028\u2029') - end += 1 diff --git a/src/yaml/error.py b/src/yaml/error.py deleted file mode 100644 index b796b4d..0000000 --- a/src/yaml/error.py +++ /dev/null @@ -1,75 +0,0 @@ - -__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError'] - -class Mark: - - def __init__(self, name, index, line, column, buffer, pointer): - self.name = name - self.index = index - self.line = line - self.column = column - self.buffer = buffer - self.pointer = pointer - - def get_snippet(self, indent=4, max_length=75): - if self.buffer is None: - return None - head = '' - start = self.pointer - while start > 0 and self.buffer[start-1] not in '\0\r\n\x85\u2028\u2029': - start -= 1 - if self.pointer-start > max_length/2-1: - head = ' ... ' - start += 5 - break - tail = '' - end = self.pointer - while end < len(self.buffer) and self.buffer[end] not in '\0\r\n\x85\u2028\u2029': - end += 1 - if end-self.pointer > max_length/2-1: - tail = ' ... ' - end -= 5 - break - snippet = self.buffer[start:end] - return ' '*indent + head + snippet + tail + '\n' \ - + ' '*(indent+self.pointer-start+len(head)) + '^' - - def __str__(self): - snippet = self.get_snippet() - where = " in \"%s\", line %d, column %d" \ - % (self.name, self.line+1, self.column+1) - if snippet is not None: - where += ":\n"+snippet - return where - -class YAMLError(Exception): - pass - -class MarkedYAMLError(YAMLError): - - def __init__(self, context=None, context_mark=None, - problem=None, problem_mark=None, note=None): - self.context = context - self.context_mark = context_mark - self.problem = problem - self.problem_mark = problem_mark - self.note = note - - def __str__(self): - lines = [] - if self.context is not None: - lines.append(self.context) - if self.context_mark is not None \ - and (self.problem is None or self.problem_mark is None - or self.context_mark.name != self.problem_mark.name - or self.context_mark.line != self.problem_mark.line - or self.context_mark.column != self.problem_mark.column): - lines.append(str(self.context_mark)) - if self.problem is not None: - lines.append(self.problem) - if self.problem_mark is not None: - lines.append(str(self.problem_mark)) - if self.note is not None: - lines.append(self.note) - return '\n'.join(lines) - diff --git a/src/yaml/events.py b/src/yaml/events.py deleted file mode 100644 index f79ad38..0000000 --- a/src/yaml/events.py +++ /dev/null @@ -1,86 +0,0 @@ - -# Abstract classes. - -class Event(object): - def __init__(self, start_mark=None, end_mark=None): - self.start_mark = start_mark - self.end_mark = end_mark - def __repr__(self): - attributes = [key for key in ['anchor', 'tag', 'implicit', 'value'] - if hasattr(self, key)] - arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) - for key in attributes]) - return '%s(%s)' % (self.__class__.__name__, arguments) - -class NodeEvent(Event): - def __init__(self, anchor, start_mark=None, end_mark=None): - self.anchor = anchor - self.start_mark = start_mark - self.end_mark = end_mark - -class CollectionStartEvent(NodeEvent): - def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None, - flow_style=None): - self.anchor = anchor - self.tag = tag - self.implicit = implicit - self.start_mark = start_mark - self.end_mark = end_mark - self.flow_style = flow_style - -class CollectionEndEvent(Event): - pass - -# Implementations. - -class StreamStartEvent(Event): - def __init__(self, start_mark=None, end_mark=None, encoding=None): - self.start_mark = start_mark - self.end_mark = end_mark - self.encoding = encoding - -class StreamEndEvent(Event): - pass - -class DocumentStartEvent(Event): - def __init__(self, start_mark=None, end_mark=None, - explicit=None, version=None, tags=None): - self.start_mark = start_mark - self.end_mark = end_mark - self.explicit = explicit - self.version = version - self.tags = tags - -class DocumentEndEvent(Event): - def __init__(self, start_mark=None, end_mark=None, - explicit=None): - self.start_mark = start_mark - self.end_mark = end_mark - self.explicit = explicit - -class AliasEvent(NodeEvent): - pass - -class ScalarEvent(NodeEvent): - def __init__(self, anchor, tag, implicit, value, - start_mark=None, end_mark=None, style=None): - self.anchor = anchor - self.tag = tag - self.implicit = implicit - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - self.style = style - -class SequenceStartEvent(CollectionStartEvent): - pass - -class SequenceEndEvent(CollectionEndEvent): - pass - -class MappingStartEvent(CollectionStartEvent): - pass - -class MappingEndEvent(CollectionEndEvent): - pass - diff --git a/src/yaml/loader.py b/src/yaml/loader.py deleted file mode 100644 index e90c112..0000000 --- a/src/yaml/loader.py +++ /dev/null @@ -1,63 +0,0 @@ - -__all__ = ['BaseLoader', 'FullLoader', 'SafeLoader', 'Loader', 'UnsafeLoader'] - -from .reader import * -from .scanner import * -from .parser import * -from .composer import * -from .constructor import * -from .resolver import * - -class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver): - - def __init__(self, stream): - Reader.__init__(self, stream) - Scanner.__init__(self) - Parser.__init__(self) - Composer.__init__(self) - BaseConstructor.__init__(self) - BaseResolver.__init__(self) - -class FullLoader(Reader, Scanner, Parser, Composer, FullConstructor, Resolver): - - def __init__(self, stream): - Reader.__init__(self, stream) - Scanner.__init__(self) - Parser.__init__(self) - Composer.__init__(self) - FullConstructor.__init__(self) - Resolver.__init__(self) - -class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver): - - def __init__(self, stream): - Reader.__init__(self, stream) - Scanner.__init__(self) - Parser.__init__(self) - Composer.__init__(self) - SafeConstructor.__init__(self) - Resolver.__init__(self) - -class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver): - - def __init__(self, stream): - Reader.__init__(self, stream) - Scanner.__init__(self) - Parser.__init__(self) - Composer.__init__(self) - Constructor.__init__(self) - Resolver.__init__(self) - -# UnsafeLoader is the same as Loader (which is and was always unsafe on -# untrusted input). Use of either Loader or UnsafeLoader should be rare, since -# FullLoad should be able to load almost all YAML safely. Loader is left intact -# to ensure backwards compatibility. -class UnsafeLoader(Reader, Scanner, Parser, Composer, Constructor, Resolver): - - def __init__(self, stream): - Reader.__init__(self, stream) - Scanner.__init__(self) - Parser.__init__(self) - Composer.__init__(self) - Constructor.__init__(self) - Resolver.__init__(self) diff --git a/src/yaml/nodes.py b/src/yaml/nodes.py deleted file mode 100644 index c4f070c..0000000 --- a/src/yaml/nodes.py +++ /dev/null @@ -1,49 +0,0 @@ - -class Node(object): - def __init__(self, tag, value, start_mark, end_mark): - self.tag = tag - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - def __repr__(self): - value = self.value - #if isinstance(value, list): - # if len(value) == 0: - # value = '' - # elif len(value) == 1: - # value = '<1 item>' - # else: - # value = '<%d items>' % len(value) - #else: - # if len(value) > 75: - # value = repr(value[:70]+u' ... ') - # else: - # value = repr(value) - value = repr(value) - return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value) - -class ScalarNode(Node): - id = 'scalar' - def __init__(self, tag, value, - start_mark=None, end_mark=None, style=None): - self.tag = tag - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - self.style = style - -class CollectionNode(Node): - def __init__(self, tag, value, - start_mark=None, end_mark=None, flow_style=None): - self.tag = tag - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - self.flow_style = flow_style - -class SequenceNode(CollectionNode): - id = 'sequence' - -class MappingNode(CollectionNode): - id = 'mapping' - diff --git a/src/yaml/parser.py b/src/yaml/parser.py deleted file mode 100644 index 13a5995..0000000 --- a/src/yaml/parser.py +++ /dev/null @@ -1,589 +0,0 @@ - -# The following YAML grammar is LL(1) and is parsed by a recursive descent -# parser. -# -# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END -# implicit_document ::= block_node DOCUMENT-END* -# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* -# block_node_or_indentless_sequence ::= -# ALIAS -# | properties (block_content | indentless_block_sequence)? -# | block_content -# | indentless_block_sequence -# block_node ::= ALIAS -# | properties block_content? -# | block_content -# flow_node ::= ALIAS -# | properties flow_content? -# | flow_content -# properties ::= TAG ANCHOR? | ANCHOR TAG? -# block_content ::= block_collection | flow_collection | SCALAR -# flow_content ::= flow_collection | SCALAR -# block_collection ::= block_sequence | block_mapping -# flow_collection ::= flow_sequence | flow_mapping -# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END -# indentless_sequence ::= (BLOCK-ENTRY block_node?)+ -# block_mapping ::= BLOCK-MAPPING_START -# ((KEY block_node_or_indentless_sequence?)? -# (VALUE block_node_or_indentless_sequence?)?)* -# BLOCK-END -# flow_sequence ::= FLOW-SEQUENCE-START -# (flow_sequence_entry FLOW-ENTRY)* -# flow_sequence_entry? -# FLOW-SEQUENCE-END -# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? -# flow_mapping ::= FLOW-MAPPING-START -# (flow_mapping_entry FLOW-ENTRY)* -# flow_mapping_entry? -# FLOW-MAPPING-END -# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? -# -# FIRST sets: -# -# stream: { STREAM-START } -# explicit_document: { DIRECTIVE DOCUMENT-START } -# implicit_document: FIRST(block_node) -# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START } -# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START } -# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } -# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } -# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START } -# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } -# block_sequence: { BLOCK-SEQUENCE-START } -# block_mapping: { BLOCK-MAPPING-START } -# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY } -# indentless_sequence: { ENTRY } -# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } -# flow_sequence: { FLOW-SEQUENCE-START } -# flow_mapping: { FLOW-MAPPING-START } -# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } -# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } - -__all__ = ['Parser', 'ParserError'] - -from .error import MarkedYAMLError -from .tokens import * -from .events import * -from .scanner import * - -class ParserError(MarkedYAMLError): - pass - -class Parser: - # Since writing a recursive-descendant parser is a straightforward task, we - # do not give many comments here. - - DEFAULT_TAGS = { - '!': '!', - '!!': 'tag:yaml.org,2002:', - } - - def __init__(self): - self.current_event = None - self.yaml_version = None - self.tag_handles = {} - self.states = [] - self.marks = [] - self.state = self.parse_stream_start - - def dispose(self): - # Reset the state attributes (to clear self-references) - self.states = [] - self.state = None - - def check_event(self, *choices): - # Check the type of the next event. - if self.current_event is None: - if self.state: - self.current_event = self.state() - if self.current_event is not None: - if not choices: - return True - for choice in choices: - if isinstance(self.current_event, choice): - return True - return False - - def peek_event(self): - # Get the next event. - if self.current_event is None: - if self.state: - self.current_event = self.state() - return self.current_event - - def get_event(self): - # Get the next event and proceed further. - if self.current_event is None: - if self.state: - self.current_event = self.state() - value = self.current_event - self.current_event = None - return value - - # stream ::= STREAM-START implicit_document? explicit_document* STREAM-END - # implicit_document ::= block_node DOCUMENT-END* - # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* - - def parse_stream_start(self): - - # Parse the stream start. - token = self.get_token() - event = StreamStartEvent(token.start_mark, token.end_mark, - encoding=token.encoding) - - # Prepare the next state. - self.state = self.parse_implicit_document_start - - return event - - def parse_implicit_document_start(self): - - # Parse an implicit document. - if not self.check_token(DirectiveToken, DocumentStartToken, - StreamEndToken): - self.tag_handles = self.DEFAULT_TAGS - token = self.peek_token() - start_mark = end_mark = token.start_mark - event = DocumentStartEvent(start_mark, end_mark, - explicit=False) - - # Prepare the next state. - self.states.append(self.parse_document_end) - self.state = self.parse_block_node - - return event - - else: - return self.parse_document_start() - - def parse_document_start(self): - - # Parse any extra document end indicators. - while self.check_token(DocumentEndToken): - self.get_token() - - # Parse an explicit document. - if not self.check_token(StreamEndToken): - token = self.peek_token() - start_mark = token.start_mark - version, tags = self.process_directives() - if not self.check_token(DocumentStartToken): - raise ParserError(None, None, - "expected '', but found %r" - % self.peek_token().id, - self.peek_token().start_mark) - token = self.get_token() - end_mark = token.end_mark - event = DocumentStartEvent(start_mark, end_mark, - explicit=True, version=version, tags=tags) - self.states.append(self.parse_document_end) - self.state = self.parse_document_content - else: - # Parse the end of the stream. - token = self.get_token() - event = StreamEndEvent(token.start_mark, token.end_mark) - assert not self.states - assert not self.marks - self.state = None - return event - - def parse_document_end(self): - - # Parse the document end. - token = self.peek_token() - start_mark = end_mark = token.start_mark - explicit = False - if self.check_token(DocumentEndToken): - token = self.get_token() - end_mark = token.end_mark - explicit = True - event = DocumentEndEvent(start_mark, end_mark, - explicit=explicit) - - # Prepare the next state. - self.state = self.parse_document_start - - return event - - def parse_document_content(self): - if self.check_token(DirectiveToken, - DocumentStartToken, DocumentEndToken, StreamEndToken): - event = self.process_empty_scalar(self.peek_token().start_mark) - self.state = self.states.pop() - return event - else: - return self.parse_block_node() - - def process_directives(self): - self.yaml_version = None - self.tag_handles = {} - while self.check_token(DirectiveToken): - token = self.get_token() - if token.name == 'YAML': - if self.yaml_version is not None: - raise ParserError(None, None, - "found duplicate YAML directive", token.start_mark) - major, minor = token.value - if major != 1: - raise ParserError(None, None, - "found incompatible YAML document (version 1.* is required)", - token.start_mark) - self.yaml_version = token.value - elif token.name == 'TAG': - handle, prefix = token.value - if handle in self.tag_handles: - raise ParserError(None, None, - "duplicate tag handle %r" % handle, - token.start_mark) - self.tag_handles[handle] = prefix - if self.tag_handles: - value = self.yaml_version, self.tag_handles.copy() - else: - value = self.yaml_version, None - for key in self.DEFAULT_TAGS: - if key not in self.tag_handles: - self.tag_handles[key] = self.DEFAULT_TAGS[key] - return value - - # block_node_or_indentless_sequence ::= ALIAS - # | properties (block_content | indentless_block_sequence)? - # | block_content - # | indentless_block_sequence - # block_node ::= ALIAS - # | properties block_content? - # | block_content - # flow_node ::= ALIAS - # | properties flow_content? - # | flow_content - # properties ::= TAG ANCHOR? | ANCHOR TAG? - # block_content ::= block_collection | flow_collection | SCALAR - # flow_content ::= flow_collection | SCALAR - # block_collection ::= block_sequence | block_mapping - # flow_collection ::= flow_sequence | flow_mapping - - def parse_block_node(self): - return self.parse_node(block=True) - - def parse_flow_node(self): - return self.parse_node() - - def parse_block_node_or_indentless_sequence(self): - return self.parse_node(block=True, indentless_sequence=True) - - def parse_node(self, block=False, indentless_sequence=False): - if self.check_token(AliasToken): - token = self.get_token() - event = AliasEvent(token.value, token.start_mark, token.end_mark) - self.state = self.states.pop() - else: - anchor = None - tag = None - start_mark = end_mark = tag_mark = None - if self.check_token(AnchorToken): - token = self.get_token() - start_mark = token.start_mark - end_mark = token.end_mark - anchor = token.value - if self.check_token(TagToken): - token = self.get_token() - tag_mark = token.start_mark - end_mark = token.end_mark - tag = token.value - elif self.check_token(TagToken): - token = self.get_token() - start_mark = tag_mark = token.start_mark - end_mark = token.end_mark - tag = token.value - if self.check_token(AnchorToken): - token = self.get_token() - end_mark = token.end_mark - anchor = token.value - if tag is not None: - handle, suffix = tag - if handle is not None: - if handle not in self.tag_handles: - raise ParserError("while parsing a node", start_mark, - "found undefined tag handle %r" % handle, - tag_mark) - tag = self.tag_handles[handle]+suffix - else: - tag = suffix - #if tag == '!': - # raise ParserError("while parsing a node", start_mark, - # "found non-specific tag '!'", tag_mark, - # "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.") - if start_mark is None: - start_mark = end_mark = self.peek_token().start_mark - event = None - implicit = (tag is None or tag == '!') - if indentless_sequence and self.check_token(BlockEntryToken): - end_mark = self.peek_token().end_mark - event = SequenceStartEvent(anchor, tag, implicit, - start_mark, end_mark) - self.state = self.parse_indentless_sequence_entry - else: - if self.check_token(ScalarToken): - token = self.get_token() - end_mark = token.end_mark - if (token.plain and tag is None) or tag == '!': - implicit = (True, False) - elif tag is None: - implicit = (False, True) - else: - implicit = (False, False) - event = ScalarEvent(anchor, tag, implicit, token.value, - start_mark, end_mark, style=token.style) - self.state = self.states.pop() - elif self.check_token(FlowSequenceStartToken): - end_mark = self.peek_token().end_mark - event = SequenceStartEvent(anchor, tag, implicit, - start_mark, end_mark, flow_style=True) - self.state = self.parse_flow_sequence_first_entry - elif self.check_token(FlowMappingStartToken): - end_mark = self.peek_token().end_mark - event = MappingStartEvent(anchor, tag, implicit, - start_mark, end_mark, flow_style=True) - self.state = self.parse_flow_mapping_first_key - elif block and self.check_token(BlockSequenceStartToken): - end_mark = self.peek_token().start_mark - event = SequenceStartEvent(anchor, tag, implicit, - start_mark, end_mark, flow_style=False) - self.state = self.parse_block_sequence_first_entry - elif block and self.check_token(BlockMappingStartToken): - end_mark = self.peek_token().start_mark - event = MappingStartEvent(anchor, tag, implicit, - start_mark, end_mark, flow_style=False) - self.state = self.parse_block_mapping_first_key - elif anchor is not None or tag is not None: - # Empty scalars are allowed even if a tag or an anchor is - # specified. - event = ScalarEvent(anchor, tag, (implicit, False), '', - start_mark, end_mark) - self.state = self.states.pop() - else: - if block: - node = 'block' - else: - node = 'flow' - token = self.peek_token() - raise ParserError("while parsing a %s node" % node, start_mark, - "expected the node content, but found %r" % token.id, - token.start_mark) - return event - - # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END - - def parse_block_sequence_first_entry(self): - token = self.get_token() - self.marks.append(token.start_mark) - return self.parse_block_sequence_entry() - - def parse_block_sequence_entry(self): - if self.check_token(BlockEntryToken): - token = self.get_token() - if not self.check_token(BlockEntryToken, BlockEndToken): - self.states.append(self.parse_block_sequence_entry) - return self.parse_block_node() - else: - self.state = self.parse_block_sequence_entry - return self.process_empty_scalar(token.end_mark) - if not self.check_token(BlockEndToken): - token = self.peek_token() - raise ParserError("while parsing a block collection", self.marks[-1], - "expected , but found %r" % token.id, token.start_mark) - token = self.get_token() - event = SequenceEndEvent(token.start_mark, token.end_mark) - self.state = self.states.pop() - self.marks.pop() - return event - - # indentless_sequence ::= (BLOCK-ENTRY block_node?)+ - - def parse_indentless_sequence_entry(self): - if self.check_token(BlockEntryToken): - token = self.get_token() - if not self.check_token(BlockEntryToken, - KeyToken, ValueToken, BlockEndToken): - self.states.append(self.parse_indentless_sequence_entry) - return self.parse_block_node() - else: - self.state = self.parse_indentless_sequence_entry - return self.process_empty_scalar(token.end_mark) - token = self.peek_token() - event = SequenceEndEvent(token.start_mark, token.start_mark) - self.state = self.states.pop() - return event - - # block_mapping ::= BLOCK-MAPPING_START - # ((KEY block_node_or_indentless_sequence?)? - # (VALUE block_node_or_indentless_sequence?)?)* - # BLOCK-END - - def parse_block_mapping_first_key(self): - token = self.get_token() - self.marks.append(token.start_mark) - return self.parse_block_mapping_key() - - def parse_block_mapping_key(self): - if self.check_token(KeyToken): - token = self.get_token() - if not self.check_token(KeyToken, ValueToken, BlockEndToken): - self.states.append(self.parse_block_mapping_value) - return self.parse_block_node_or_indentless_sequence() - else: - self.state = self.parse_block_mapping_value - return self.process_empty_scalar(token.end_mark) - if not self.check_token(BlockEndToken): - token = self.peek_token() - raise ParserError("while parsing a block mapping", self.marks[-1], - "expected , but found %r" % token.id, token.start_mark) - token = self.get_token() - event = MappingEndEvent(token.start_mark, token.end_mark) - self.state = self.states.pop() - self.marks.pop() - return event - - def parse_block_mapping_value(self): - if self.check_token(ValueToken): - token = self.get_token() - if not self.check_token(KeyToken, ValueToken, BlockEndToken): - self.states.append(self.parse_block_mapping_key) - return self.parse_block_node_or_indentless_sequence() - else: - self.state = self.parse_block_mapping_key - return self.process_empty_scalar(token.end_mark) - else: - self.state = self.parse_block_mapping_key - token = self.peek_token() - return self.process_empty_scalar(token.start_mark) - - # flow_sequence ::= FLOW-SEQUENCE-START - # (flow_sequence_entry FLOW-ENTRY)* - # flow_sequence_entry? - # FLOW-SEQUENCE-END - # flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - # - # Note that while production rules for both flow_sequence_entry and - # flow_mapping_entry are equal, their interpretations are different. - # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?` - # generate an inline mapping (set syntax). - - def parse_flow_sequence_first_entry(self): - token = self.get_token() - self.marks.append(token.start_mark) - return self.parse_flow_sequence_entry(first=True) - - def parse_flow_sequence_entry(self, first=False): - if not self.check_token(FlowSequenceEndToken): - if not first: - if self.check_token(FlowEntryToken): - self.get_token() - else: - token = self.peek_token() - raise ParserError("while parsing a flow sequence", self.marks[-1], - "expected ',' or ']', but got %r" % token.id, token.start_mark) - - if self.check_token(KeyToken): - token = self.peek_token() - event = MappingStartEvent(None, None, True, - token.start_mark, token.end_mark, - flow_style=True) - self.state = self.parse_flow_sequence_entry_mapping_key - return event - elif not self.check_token(FlowSequenceEndToken): - self.states.append(self.parse_flow_sequence_entry) - return self.parse_flow_node() - token = self.get_token() - event = SequenceEndEvent(token.start_mark, token.end_mark) - self.state = self.states.pop() - self.marks.pop() - return event - - def parse_flow_sequence_entry_mapping_key(self): - token = self.get_token() - if not self.check_token(ValueToken, - FlowEntryToken, FlowSequenceEndToken): - self.states.append(self.parse_flow_sequence_entry_mapping_value) - return self.parse_flow_node() - else: - self.state = self.parse_flow_sequence_entry_mapping_value - return self.process_empty_scalar(token.end_mark) - - def parse_flow_sequence_entry_mapping_value(self): - if self.check_token(ValueToken): - token = self.get_token() - if not self.check_token(FlowEntryToken, FlowSequenceEndToken): - self.states.append(self.parse_flow_sequence_entry_mapping_end) - return self.parse_flow_node() - else: - self.state = self.parse_flow_sequence_entry_mapping_end - return self.process_empty_scalar(token.end_mark) - else: - self.state = self.parse_flow_sequence_entry_mapping_end - token = self.peek_token() - return self.process_empty_scalar(token.start_mark) - - def parse_flow_sequence_entry_mapping_end(self): - self.state = self.parse_flow_sequence_entry - token = self.peek_token() - return MappingEndEvent(token.start_mark, token.start_mark) - - # flow_mapping ::= FLOW-MAPPING-START - # (flow_mapping_entry FLOW-ENTRY)* - # flow_mapping_entry? - # FLOW-MAPPING-END - # flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - - def parse_flow_mapping_first_key(self): - token = self.get_token() - self.marks.append(token.start_mark) - return self.parse_flow_mapping_key(first=True) - - def parse_flow_mapping_key(self, first=False): - if not self.check_token(FlowMappingEndToken): - if not first: - if self.check_token(FlowEntryToken): - self.get_token() - else: - token = self.peek_token() - raise ParserError("while parsing a flow mapping", self.marks[-1], - "expected ',' or '}', but got %r" % token.id, token.start_mark) - if self.check_token(KeyToken): - token = self.get_token() - if not self.check_token(ValueToken, - FlowEntryToken, FlowMappingEndToken): - self.states.append(self.parse_flow_mapping_value) - return self.parse_flow_node() - else: - self.state = self.parse_flow_mapping_value - return self.process_empty_scalar(token.end_mark) - elif not self.check_token(FlowMappingEndToken): - self.states.append(self.parse_flow_mapping_empty_value) - return self.parse_flow_node() - token = self.get_token() - event = MappingEndEvent(token.start_mark, token.end_mark) - self.state = self.states.pop() - self.marks.pop() - return event - - def parse_flow_mapping_value(self): - if self.check_token(ValueToken): - token = self.get_token() - if not self.check_token(FlowEntryToken, FlowMappingEndToken): - self.states.append(self.parse_flow_mapping_key) - return self.parse_flow_node() - else: - self.state = self.parse_flow_mapping_key - return self.process_empty_scalar(token.end_mark) - else: - self.state = self.parse_flow_mapping_key - token = self.peek_token() - return self.process_empty_scalar(token.start_mark) - - def parse_flow_mapping_empty_value(self): - self.state = self.parse_flow_mapping_key - return self.process_empty_scalar(self.peek_token().start_mark) - - def process_empty_scalar(self, mark): - return ScalarEvent(None, None, (True, False), '', mark, mark) - diff --git a/src/yaml/reader.py b/src/yaml/reader.py deleted file mode 100644 index 774b021..0000000 --- a/src/yaml/reader.py +++ /dev/null @@ -1,185 +0,0 @@ -# This module contains abstractions for the input stream. You don't have to -# looks further, there are no pretty code. -# -# We define two classes here. -# -# Mark(source, line, column) -# It's just a record and its only use is producing nice error messages. -# Parser does not use it for any other purposes. -# -# Reader(source, data) -# Reader determines the encoding of `data` and converts it to unicode. -# Reader provides the following methods and attributes: -# reader.peek(length=1) - return the next `length` characters -# reader.forward(length=1) - move the current position to `length` characters. -# reader.index - the number of the current character. -# reader.line, stream.column - the line and the column of the current character. - -__all__ = ['Reader', 'ReaderError'] - -from .error import YAMLError, Mark - -import codecs, re - -class ReaderError(YAMLError): - - def __init__(self, name, position, character, encoding, reason): - self.name = name - self.character = character - self.position = position - self.encoding = encoding - self.reason = reason - - def __str__(self): - if isinstance(self.character, bytes): - return "'%s' codec can't decode byte #x%02x: %s\n" \ - " in \"%s\", position %d" \ - % (self.encoding, ord(self.character), self.reason, - self.name, self.position) - else: - return "unacceptable character #x%04x: %s\n" \ - " in \"%s\", position %d" \ - % (self.character, self.reason, - self.name, self.position) - -class Reader(object): - # Reader: - # - determines the data encoding and converts it to a unicode string, - # - checks if characters are in allowed range, - # - adds '\0' to the end. - - # Reader accepts - # - a `bytes` object, - # - a `str` object, - # - a file-like object with its `read` method returning `str`, - # - a file-like object with its `read` method returning `unicode`. - - # Yeah, it's ugly and slow. - - def __init__(self, stream): - self.name = None - self.stream = None - self.stream_pointer = 0 - self.eof = True - self.buffer = '' - self.pointer = 0 - self.raw_buffer = None - self.raw_decode = None - self.encoding = None - self.index = 0 - self.line = 0 - self.column = 0 - if isinstance(stream, str): - self.name = "" - self.check_printable(stream) - self.buffer = stream+'\0' - elif isinstance(stream, bytes): - self.name = "" - self.raw_buffer = stream - self.determine_encoding() - else: - self.stream = stream - self.name = getattr(stream, 'name', "") - self.eof = False - self.raw_buffer = None - self.determine_encoding() - - def peek(self, index=0): - try: - return self.buffer[self.pointer+index] - except IndexError: - self.update(index+1) - return self.buffer[self.pointer+index] - - def prefix(self, length=1): - if self.pointer+length >= len(self.buffer): - self.update(length) - return self.buffer[self.pointer:self.pointer+length] - - def forward(self, length=1): - if self.pointer+length+1 >= len(self.buffer): - self.update(length+1) - while length: - ch = self.buffer[self.pointer] - self.pointer += 1 - self.index += 1 - if ch in '\n\x85\u2028\u2029' \ - or (ch == '\r' and self.buffer[self.pointer] != '\n'): - self.line += 1 - self.column = 0 - elif ch != '\uFEFF': - self.column += 1 - length -= 1 - - def get_mark(self): - if self.stream is None: - return Mark(self.name, self.index, self.line, self.column, - self.buffer, self.pointer) - else: - return Mark(self.name, self.index, self.line, self.column, - None, None) - - def determine_encoding(self): - while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2): - self.update_raw() - if isinstance(self.raw_buffer, bytes): - if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): - self.raw_decode = codecs.utf_16_le_decode - self.encoding = 'utf-16-le' - elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): - self.raw_decode = codecs.utf_16_be_decode - self.encoding = 'utf-16-be' - else: - self.raw_decode = codecs.utf_8_decode - self.encoding = 'utf-8' - self.update(1) - - NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]') - def check_printable(self, data): - match = self.NON_PRINTABLE.search(data) - if match: - character = match.group() - position = self.index+(len(self.buffer)-self.pointer)+match.start() - raise ReaderError(self.name, position, ord(character), - 'unicode', "special characters are not allowed") - - def update(self, length): - if self.raw_buffer is None: - return - self.buffer = self.buffer[self.pointer:] - self.pointer = 0 - while len(self.buffer) < length: - if not self.eof: - self.update_raw() - if self.raw_decode is not None: - try: - data, converted = self.raw_decode(self.raw_buffer, - 'strict', self.eof) - except UnicodeDecodeError as exc: - character = self.raw_buffer[exc.start] - if self.stream is not None: - position = self.stream_pointer-len(self.raw_buffer)+exc.start - else: - position = exc.start - raise ReaderError(self.name, position, character, - exc.encoding, exc.reason) - else: - data = self.raw_buffer - converted = len(data) - self.check_printable(data) - self.buffer += data - self.raw_buffer = self.raw_buffer[converted:] - if self.eof: - self.buffer += '\0' - self.raw_buffer = None - break - - def update_raw(self, size=4096): - data = self.stream.read(size) - if self.raw_buffer is None: - self.raw_buffer = data - else: - self.raw_buffer += data - self.stream_pointer += len(data) - if not data: - self.eof = True diff --git a/src/yaml/representer.py b/src/yaml/representer.py deleted file mode 100644 index 3b0b192..0000000 --- a/src/yaml/representer.py +++ /dev/null @@ -1,389 +0,0 @@ - -__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer', - 'RepresenterError'] - -from .error import * -from .nodes import * - -import datetime, copyreg, types, base64, collections - -class RepresenterError(YAMLError): - pass - -class BaseRepresenter: - - yaml_representers = {} - yaml_multi_representers = {} - - def __init__(self, default_style=None, default_flow_style=False, sort_keys=True): - self.default_style = default_style - self.sort_keys = sort_keys - self.default_flow_style = default_flow_style - self.represented_objects = {} - self.object_keeper = [] - self.alias_key = None - - def represent(self, data): - node = self.represent_data(data) - self.serialize(node) - self.represented_objects = {} - self.object_keeper = [] - self.alias_key = None - - def represent_data(self, data): - if self.ignore_aliases(data): - self.alias_key = None - else: - self.alias_key = id(data) - if self.alias_key is not None: - if self.alias_key in self.represented_objects: - node = self.represented_objects[self.alias_key] - #if node is None: - # raise RepresenterError("recursive objects are not allowed: %r" % data) - return node - #self.represented_objects[alias_key] = None - self.object_keeper.append(data) - data_types = type(data).__mro__ - if data_types[0] in self.yaml_representers: - node = self.yaml_representers[data_types[0]](self, data) - else: - for data_type in data_types: - if data_type in self.yaml_multi_representers: - node = self.yaml_multi_representers[data_type](self, data) - break - else: - if None in self.yaml_multi_representers: - node = self.yaml_multi_representers[None](self, data) - elif None in self.yaml_representers: - node = self.yaml_representers[None](self, data) - else: - node = ScalarNode(None, str(data)) - #if alias_key is not None: - # self.represented_objects[alias_key] = node - return node - - @classmethod - def add_representer(cls, data_type, representer): - if not 'yaml_representers' in cls.__dict__: - cls.yaml_representers = cls.yaml_representers.copy() - cls.yaml_representers[data_type] = representer - - @classmethod - def add_multi_representer(cls, data_type, representer): - if not 'yaml_multi_representers' in cls.__dict__: - cls.yaml_multi_representers = cls.yaml_multi_representers.copy() - cls.yaml_multi_representers[data_type] = representer - - def represent_scalar(self, tag, value, style=None): - if style is None: - style = self.default_style - node = ScalarNode(tag, value, style=style) - if self.alias_key is not None: - self.represented_objects[self.alias_key] = node - return node - - def represent_sequence(self, tag, sequence, flow_style=None): - value = [] - node = SequenceNode(tag, value, flow_style=flow_style) - if self.alias_key is not None: - self.represented_objects[self.alias_key] = node - best_style = True - for item in sequence: - node_item = self.represent_data(item) - if not (isinstance(node_item, ScalarNode) and not node_item.style): - best_style = False - value.append(node_item) - if flow_style is None: - if self.default_flow_style is not None: - node.flow_style = self.default_flow_style - else: - node.flow_style = best_style - return node - - def represent_mapping(self, tag, mapping, flow_style=None): - value = [] - node = MappingNode(tag, value, flow_style=flow_style) - if self.alias_key is not None: - self.represented_objects[self.alias_key] = node - best_style = True - if hasattr(mapping, 'items'): - mapping = list(mapping.items()) - if self.sort_keys: - try: - mapping = sorted(mapping) - except TypeError: - pass - for item_key, item_value in mapping: - node_key = self.represent_data(item_key) - node_value = self.represent_data(item_value) - if not (isinstance(node_key, ScalarNode) and not node_key.style): - best_style = False - if not (isinstance(node_value, ScalarNode) and not node_value.style): - best_style = False - value.append((node_key, node_value)) - if flow_style is None: - if self.default_flow_style is not None: - node.flow_style = self.default_flow_style - else: - node.flow_style = best_style - return node - - def ignore_aliases(self, data): - return False - -class SafeRepresenter(BaseRepresenter): - - def ignore_aliases(self, data): - if data is None: - return True - if isinstance(data, tuple) and data == (): - return True - if isinstance(data, (str, bytes, bool, int, float)): - return True - - def represent_none(self, data): - return self.represent_scalar('tag:yaml.org,2002:null', 'null') - - def represent_str(self, data): - return self.represent_scalar('tag:yaml.org,2002:str', data) - - def represent_binary(self, data): - if hasattr(base64, 'encodebytes'): - data = base64.encodebytes(data).decode('ascii') - else: - data = base64.encodestring(data).decode('ascii') - return self.represent_scalar('tag:yaml.org,2002:binary', data, style='|') - - def represent_bool(self, data): - if data: - value = 'true' - else: - value = 'false' - return self.represent_scalar('tag:yaml.org,2002:bool', value) - - def represent_int(self, data): - return self.represent_scalar('tag:yaml.org,2002:int', str(data)) - - inf_value = 1e300 - while repr(inf_value) != repr(inf_value*inf_value): - inf_value *= inf_value - - def represent_float(self, data): - if data != data or (data == 0.0 and data == 1.0): - value = '.nan' - elif data == self.inf_value: - value = '.inf' - elif data == -self.inf_value: - value = '-.inf' - else: - value = repr(data).lower() - # Note that in some cases `repr(data)` represents a float number - # without the decimal parts. For instance: - # >>> repr(1e17) - # '1e17' - # Unfortunately, this is not a valid float representation according - # to the definition of the `!!float` tag. We fix this by adding - # '.0' before the 'e' symbol. - if '.' not in value and 'e' in value: - value = value.replace('e', '.0e', 1) - return self.represent_scalar('tag:yaml.org,2002:float', value) - - def represent_list(self, data): - #pairs = (len(data) > 0 and isinstance(data, list)) - #if pairs: - # for item in data: - # if not isinstance(item, tuple) or len(item) != 2: - # pairs = False - # break - #if not pairs: - return self.represent_sequence('tag:yaml.org,2002:seq', data) - #value = [] - #for item_key, item_value in data: - # value.append(self.represent_mapping(u'tag:yaml.org,2002:map', - # [(item_key, item_value)])) - #return SequenceNode(u'tag:yaml.org,2002:pairs', value) - - def represent_dict(self, data): - return self.represent_mapping('tag:yaml.org,2002:map', data) - - def represent_set(self, data): - value = {} - for key in data: - value[key] = None - return self.represent_mapping('tag:yaml.org,2002:set', value) - - def represent_date(self, data): - value = data.isoformat() - return self.represent_scalar('tag:yaml.org,2002:timestamp', value) - - def represent_datetime(self, data): - value = data.isoformat(' ') - return self.represent_scalar('tag:yaml.org,2002:timestamp', value) - - def represent_yaml_object(self, tag, data, cls, flow_style=None): - if hasattr(data, '__getstate__'): - state = data.__getstate__() - else: - state = data.__dict__.copy() - return self.represent_mapping(tag, state, flow_style=flow_style) - - def represent_undefined(self, data): - raise RepresenterError("cannot represent an object", data) - -SafeRepresenter.add_representer(type(None), - SafeRepresenter.represent_none) - -SafeRepresenter.add_representer(str, - SafeRepresenter.represent_str) - -SafeRepresenter.add_representer(bytes, - SafeRepresenter.represent_binary) - -SafeRepresenter.add_representer(bool, - SafeRepresenter.represent_bool) - -SafeRepresenter.add_representer(int, - SafeRepresenter.represent_int) - -SafeRepresenter.add_representer(float, - SafeRepresenter.represent_float) - -SafeRepresenter.add_representer(list, - SafeRepresenter.represent_list) - -SafeRepresenter.add_representer(tuple, - SafeRepresenter.represent_list) - -SafeRepresenter.add_representer(dict, - SafeRepresenter.represent_dict) - -SafeRepresenter.add_representer(set, - SafeRepresenter.represent_set) - -SafeRepresenter.add_representer(datetime.date, - SafeRepresenter.represent_date) - -SafeRepresenter.add_representer(datetime.datetime, - SafeRepresenter.represent_datetime) - -SafeRepresenter.add_representer(None, - SafeRepresenter.represent_undefined) - -class Representer(SafeRepresenter): - - def represent_complex(self, data): - if data.imag == 0.0: - data = '%r' % data.real - elif data.real == 0.0: - data = '%rj' % data.imag - elif data.imag > 0: - data = '%r+%rj' % (data.real, data.imag) - else: - data = '%r%rj' % (data.real, data.imag) - return self.represent_scalar('tag:yaml.org,2002:python/complex', data) - - def represent_tuple(self, data): - return self.represent_sequence('tag:yaml.org,2002:python/tuple', data) - - def represent_name(self, data): - name = '%s.%s' % (data.__module__, data.__name__) - return self.represent_scalar('tag:yaml.org,2002:python/name:'+name, '') - - def represent_module(self, data): - return self.represent_scalar( - 'tag:yaml.org,2002:python/module:'+data.__name__, '') - - def represent_object(self, data): - # We use __reduce__ API to save the data. data.__reduce__ returns - # a tuple of length 2-5: - # (function, args, state, listitems, dictitems) - - # For reconstructing, we calls function(*args), then set its state, - # listitems, and dictitems if they are not None. - - # A special case is when function.__name__ == '__newobj__'. In this - # case we create the object with args[0].__new__(*args). - - # Another special case is when __reduce__ returns a string - we don't - # support it. - - # We produce a !!python/object, !!python/object/new or - # !!python/object/apply node. - - cls = type(data) - if cls in copyreg.dispatch_table: - reduce = copyreg.dispatch_table[cls](data) - elif hasattr(data, '__reduce_ex__'): - reduce = data.__reduce_ex__(2) - elif hasattr(data, '__reduce__'): - reduce = data.__reduce__() - else: - raise RepresenterError("cannot represent an object", data) - reduce = (list(reduce)+[None]*5)[:5] - function, args, state, listitems, dictitems = reduce - args = list(args) - if state is None: - state = {} - if listitems is not None: - listitems = list(listitems) - if dictitems is not None: - dictitems = dict(dictitems) - if function.__name__ == '__newobj__': - function = args[0] - args = args[1:] - tag = 'tag:yaml.org,2002:python/object/new:' - newobj = True - else: - tag = 'tag:yaml.org,2002:python/object/apply:' - newobj = False - function_name = '%s.%s' % (function.__module__, function.__name__) - if not args and not listitems and not dictitems \ - and isinstance(state, dict) and newobj: - return self.represent_mapping( - 'tag:yaml.org,2002:python/object:'+function_name, state) - if not listitems and not dictitems \ - and isinstance(state, dict) and not state: - return self.represent_sequence(tag+function_name, args) - value = {} - if args: - value['args'] = args - if state or not isinstance(state, dict): - value['state'] = state - if listitems: - value['listitems'] = listitems - if dictitems: - value['dictitems'] = dictitems - return self.represent_mapping(tag+function_name, value) - - def represent_ordered_dict(self, data): - # Provide uniform representation across different Python versions. - data_type = type(data) - tag = 'tag:yaml.org,2002:python/object/apply:%s.%s' \ - % (data_type.__module__, data_type.__name__) - items = [[key, value] for key, value in data.items()] - return self.represent_sequence(tag, [items]) - -Representer.add_representer(complex, - Representer.represent_complex) - -Representer.add_representer(tuple, - Representer.represent_tuple) - -Representer.add_representer(type, - Representer.represent_name) - -Representer.add_representer(collections.OrderedDict, - Representer.represent_ordered_dict) - -Representer.add_representer(types.FunctionType, - Representer.represent_name) - -Representer.add_representer(types.BuiltinFunctionType, - Representer.represent_name) - -Representer.add_representer(types.ModuleType, - Representer.represent_module) - -Representer.add_multi_representer(object, - Representer.represent_object) - diff --git a/src/yaml/resolver.py b/src/yaml/resolver.py deleted file mode 100644 index 02b82e7..0000000 --- a/src/yaml/resolver.py +++ /dev/null @@ -1,227 +0,0 @@ - -__all__ = ['BaseResolver', 'Resolver'] - -from .error import * -from .nodes import * - -import re - -class ResolverError(YAMLError): - pass - -class BaseResolver: - - DEFAULT_SCALAR_TAG = 'tag:yaml.org,2002:str' - DEFAULT_SEQUENCE_TAG = 'tag:yaml.org,2002:seq' - DEFAULT_MAPPING_TAG = 'tag:yaml.org,2002:map' - - yaml_implicit_resolvers = {} - yaml_path_resolvers = {} - - def __init__(self): - self.resolver_exact_paths = [] - self.resolver_prefix_paths = [] - - @classmethod - def add_implicit_resolver(cls, tag, regexp, first): - if not 'yaml_implicit_resolvers' in cls.__dict__: - implicit_resolvers = {} - for key in cls.yaml_implicit_resolvers: - implicit_resolvers[key] = cls.yaml_implicit_resolvers[key][:] - cls.yaml_implicit_resolvers = implicit_resolvers - if first is None: - first = [None] - for ch in first: - cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp)) - - @classmethod - def add_path_resolver(cls, tag, path, kind=None): - # Note: `add_path_resolver` is experimental. The API could be changed. - # `new_path` is a pattern that is matched against the path from the - # root to the node that is being considered. `node_path` elements are - # tuples `(node_check, index_check)`. `node_check` is a node class: - # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None` - # matches any kind of a node. `index_check` could be `None`, a boolean - # value, a string value, or a number. `None` and `False` match against - # any _value_ of sequence and mapping nodes. `True` matches against - # any _key_ of a mapping node. A string `index_check` matches against - # a mapping value that corresponds to a scalar key which content is - # equal to the `index_check` value. An integer `index_check` matches - # against a sequence value with the index equal to `index_check`. - if not 'yaml_path_resolvers' in cls.__dict__: - cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy() - new_path = [] - for element in path: - if isinstance(element, (list, tuple)): - if len(element) == 2: - node_check, index_check = element - elif len(element) == 1: - node_check = element[0] - index_check = True - else: - raise ResolverError("Invalid path element: %s" % element) - else: - node_check = None - index_check = element - if node_check is str: - node_check = ScalarNode - elif node_check is list: - node_check = SequenceNode - elif node_check is dict: - node_check = MappingNode - elif node_check not in [ScalarNode, SequenceNode, MappingNode] \ - and not isinstance(node_check, str) \ - and node_check is not None: - raise ResolverError("Invalid node checker: %s" % node_check) - if not isinstance(index_check, (str, int)) \ - and index_check is not None: - raise ResolverError("Invalid index checker: %s" % index_check) - new_path.append((node_check, index_check)) - if kind is str: - kind = ScalarNode - elif kind is list: - kind = SequenceNode - elif kind is dict: - kind = MappingNode - elif kind not in [ScalarNode, SequenceNode, MappingNode] \ - and kind is not None: - raise ResolverError("Invalid node kind: %s" % kind) - cls.yaml_path_resolvers[tuple(new_path), kind] = tag - - def descend_resolver(self, current_node, current_index): - if not self.yaml_path_resolvers: - return - exact_paths = {} - prefix_paths = [] - if current_node: - depth = len(self.resolver_prefix_paths) - for path, kind in self.resolver_prefix_paths[-1]: - if self.check_resolver_prefix(depth, path, kind, - current_node, current_index): - if len(path) > depth: - prefix_paths.append((path, kind)) - else: - exact_paths[kind] = self.yaml_path_resolvers[path, kind] - else: - for path, kind in self.yaml_path_resolvers: - if not path: - exact_paths[kind] = self.yaml_path_resolvers[path, kind] - else: - prefix_paths.append((path, kind)) - self.resolver_exact_paths.append(exact_paths) - self.resolver_prefix_paths.append(prefix_paths) - - def ascend_resolver(self): - if not self.yaml_path_resolvers: - return - self.resolver_exact_paths.pop() - self.resolver_prefix_paths.pop() - - def check_resolver_prefix(self, depth, path, kind, - current_node, current_index): - node_check, index_check = path[depth-1] - if isinstance(node_check, str): - if current_node.tag != node_check: - return - elif node_check is not None: - if not isinstance(current_node, node_check): - return - if index_check is True and current_index is not None: - return - if (index_check is False or index_check is None) \ - and current_index is None: - return - if isinstance(index_check, str): - if not (isinstance(current_index, ScalarNode) - and index_check == current_index.value): - return - elif isinstance(index_check, int) and not isinstance(index_check, bool): - if index_check != current_index: - return - return True - - def resolve(self, kind, value, implicit): - if kind is ScalarNode and implicit[0]: - if value == '': - resolvers = self.yaml_implicit_resolvers.get('', []) - else: - resolvers = self.yaml_implicit_resolvers.get(value[0], []) - resolvers += self.yaml_implicit_resolvers.get(None, []) - for tag, regexp in resolvers: - if regexp.match(value): - return tag - implicit = implicit[1] - if self.yaml_path_resolvers: - exact_paths = self.resolver_exact_paths[-1] - if kind in exact_paths: - return exact_paths[kind] - if None in exact_paths: - return exact_paths[None] - if kind is ScalarNode: - return self.DEFAULT_SCALAR_TAG - elif kind is SequenceNode: - return self.DEFAULT_SEQUENCE_TAG - elif kind is MappingNode: - return self.DEFAULT_MAPPING_TAG - -class Resolver(BaseResolver): - pass - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:bool', - re.compile(r'''^(?:yes|Yes|YES|no|No|NO - |true|True|TRUE|false|False|FALSE - |on|On|ON|off|Off|OFF)$''', re.X), - list('yYnNtTfFoO')) - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:float', - re.compile(r'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)? - |\.[0-9_]+(?:[eE][-+][0-9]+)? - |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]* - |[-+]?\.(?:inf|Inf|INF) - |\.(?:nan|NaN|NAN))$''', re.X), - list('-+0123456789.')) - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:int', - re.compile(r'''^(?:[-+]?0b[0-1_]+ - |[-+]?0[0-7_]+ - |[-+]?(?:0|[1-9][0-9_]*) - |[-+]?0x[0-9a-fA-F_]+ - |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X), - list('-+0123456789')) - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:merge', - re.compile(r'^(?:<<)$'), - ['<']) - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:null', - re.compile(r'''^(?: ~ - |null|Null|NULL - | )$''', re.X), - ['~', 'n', 'N', '']) - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:timestamp', - re.compile(r'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] - |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]? - (?:[Tt]|[ \t]+)[0-9][0-9]? - :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)? - (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X), - list('0123456789')) - -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:value', - re.compile(r'^(?:=)$'), - ['=']) - -# The following resolver is only for documentation purposes. It cannot work -# because plain scalars cannot start with '!', '&', or '*'. -Resolver.add_implicit_resolver( - 'tag:yaml.org,2002:yaml', - re.compile(r'^(?:!|&|\*)$'), - list('!&*')) - diff --git a/src/yaml/scanner.py b/src/yaml/scanner.py deleted file mode 100644 index 7437ede..0000000 --- a/src/yaml/scanner.py +++ /dev/null @@ -1,1435 +0,0 @@ - -# Scanner produces tokens of the following types: -# STREAM-START -# STREAM-END -# DIRECTIVE(name, value) -# DOCUMENT-START -# DOCUMENT-END -# BLOCK-SEQUENCE-START -# BLOCK-MAPPING-START -# BLOCK-END -# FLOW-SEQUENCE-START -# FLOW-MAPPING-START -# FLOW-SEQUENCE-END -# FLOW-MAPPING-END -# BLOCK-ENTRY -# FLOW-ENTRY -# KEY -# VALUE -# ALIAS(value) -# ANCHOR(value) -# TAG(value) -# SCALAR(value, plain, style) -# -# Read comments in the Scanner code for more details. -# - -__all__ = ['Scanner', 'ScannerError'] - -from .error import MarkedYAMLError -from .tokens import * - -class ScannerError(MarkedYAMLError): - pass - -class SimpleKey: - # See below simple keys treatment. - - def __init__(self, token_number, required, index, line, column, mark): - self.token_number = token_number - self.required = required - self.index = index - self.line = line - self.column = column - self.mark = mark - -class Scanner: - - def __init__(self): - """Initialize the scanner.""" - # It is assumed that Scanner and Reader will have a common descendant. - # Reader do the dirty work of checking for BOM and converting the - # input data to Unicode. It also adds NUL to the end. - # - # Reader supports the following methods - # self.peek(i=0) # peek the next i-th character - # self.prefix(l=1) # peek the next l characters - # self.forward(l=1) # read the next l characters and move the pointer. - - # Had we reached the end of the stream? - self.done = False - - # The number of unclosed '{' and '['. `flow_level == 0` means block - # context. - self.flow_level = 0 - - # List of processed tokens that are not yet emitted. - self.tokens = [] - - # Add the STREAM-START token. - self.fetch_stream_start() - - # Number of tokens that were emitted through the `get_token` method. - self.tokens_taken = 0 - - # The current indentation level. - self.indent = -1 - - # Past indentation levels. - self.indents = [] - - # Variables related to simple keys treatment. - - # A simple key is a key that is not denoted by the '?' indicator. - # Example of simple keys: - # --- - # block simple key: value - # ? not a simple key: - # : { flow simple key: value } - # We emit the KEY token before all keys, so when we find a potential - # simple key, we try to locate the corresponding ':' indicator. - # Simple keys should be limited to a single line and 1024 characters. - - # Can a simple key start at the current position? A simple key may - # start: - # - at the beginning of the line, not counting indentation spaces - # (in block context), - # - after '{', '[', ',' (in the flow context), - # - after '?', ':', '-' (in the block context). - # In the block context, this flag also signifies if a block collection - # may start at the current position. - self.allow_simple_key = True - - # Keep track of possible simple keys. This is a dictionary. The key - # is `flow_level`; there can be no more that one possible simple key - # for each level. The value is a SimpleKey record: - # (token_number, required, index, line, column, mark) - # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), - # '[', or '{' tokens. - self.possible_simple_keys = {} - - # Public methods. - - def check_token(self, *choices): - # Check if the next token is one of the given types. - while self.need_more_tokens(): - self.fetch_more_tokens() - if self.tokens: - if not choices: - return True - for choice in choices: - if isinstance(self.tokens[0], choice): - return True - return False - - def peek_token(self): - # Return the next token, but do not delete if from the queue. - # Return None if no more tokens. - while self.need_more_tokens(): - self.fetch_more_tokens() - if self.tokens: - return self.tokens[0] - else: - return None - - def get_token(self): - # Return the next token. - while self.need_more_tokens(): - self.fetch_more_tokens() - if self.tokens: - self.tokens_taken += 1 - return self.tokens.pop(0) - - # Private methods. - - def need_more_tokens(self): - if self.done: - return False - if not self.tokens: - return True - # The current token may be a potential simple key, so we - # need to look further. - self.stale_possible_simple_keys() - if self.next_possible_simple_key() == self.tokens_taken: - return True - - def fetch_more_tokens(self): - - # Eat whitespaces and comments until we reach the next token. - self.scan_to_next_token() - - # Remove obsolete possible simple keys. - self.stale_possible_simple_keys() - - # Compare the current indentation and column. It may add some tokens - # and decrease the current indentation level. - self.unwind_indent(self.column) - - # Peek the next character. - ch = self.peek() - - # Is it the end of stream? - if ch == '\0': - return self.fetch_stream_end() - - # Is it a directive? - if ch == '%' and self.check_directive(): - return self.fetch_directive() - - # Is it the document start? - if ch == '-' and self.check_document_start(): - return self.fetch_document_start() - - # Is it the document end? - if ch == '.' and self.check_document_end(): - return self.fetch_document_end() - - # TODO: support for BOM within a stream. - #if ch == '\uFEFF': - # return self.fetch_bom() <-- issue BOMToken - - # Note: the order of the following checks is NOT significant. - - # Is it the flow sequence start indicator? - if ch == '[': - return self.fetch_flow_sequence_start() - - # Is it the flow mapping start indicator? - if ch == '{': - return self.fetch_flow_mapping_start() - - # Is it the flow sequence end indicator? - if ch == ']': - return self.fetch_flow_sequence_end() - - # Is it the flow mapping end indicator? - if ch == '}': - return self.fetch_flow_mapping_end() - - # Is it the flow entry indicator? - if ch == ',': - return self.fetch_flow_entry() - - # Is it the block entry indicator? - if ch == '-' and self.check_block_entry(): - return self.fetch_block_entry() - - # Is it the key indicator? - if ch == '?' and self.check_key(): - return self.fetch_key() - - # Is it the value indicator? - if ch == ':' and self.check_value(): - return self.fetch_value() - - # Is it an alias? - if ch == '*': - return self.fetch_alias() - - # Is it an anchor? - if ch == '&': - return self.fetch_anchor() - - # Is it a tag? - if ch == '!': - return self.fetch_tag() - - # Is it a literal scalar? - if ch == '|' and not self.flow_level: - return self.fetch_literal() - - # Is it a folded scalar? - if ch == '>' and not self.flow_level: - return self.fetch_folded() - - # Is it a single quoted scalar? - if ch == '\'': - return self.fetch_single() - - # Is it a double quoted scalar? - if ch == '\"': - return self.fetch_double() - - # It must be a plain scalar then. - if self.check_plain(): - return self.fetch_plain() - - # No? It's an error. Let's produce a nice error message. - raise ScannerError("while scanning for the next token", None, - "found character %r that cannot start any token" % ch, - self.get_mark()) - - # Simple keys treatment. - - def next_possible_simple_key(self): - # Return the number of the nearest possible simple key. Actually we - # don't need to loop through the whole dictionary. We may replace it - # with the following code: - # if not self.possible_simple_keys: - # return None - # return self.possible_simple_keys[ - # min(self.possible_simple_keys.keys())].token_number - min_token_number = None - for level in self.possible_simple_keys: - key = self.possible_simple_keys[level] - if min_token_number is None or key.token_number < min_token_number: - min_token_number = key.token_number - return min_token_number - - def stale_possible_simple_keys(self): - # Remove entries that are no longer possible simple keys. According to - # the YAML specification, simple keys - # - should be limited to a single line, - # - should be no longer than 1024 characters. - # Disabling this procedure will allow simple keys of any length and - # height (may cause problems if indentation is broken though). - for level in list(self.possible_simple_keys): - key = self.possible_simple_keys[level] - if key.line != self.line \ - or self.index-key.index > 1024: - if key.required: - raise ScannerError("while scanning a simple key", key.mark, - "could not find expected ':'", self.get_mark()) - del self.possible_simple_keys[level] - - def save_possible_simple_key(self): - # The next token may start a simple key. We check if it's possible - # and save its position. This function is called for - # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'. - - # Check if a simple key is required at the current position. - required = not self.flow_level and self.indent == self.column - - # The next token might be a simple key. Let's save it's number and - # position. - if self.allow_simple_key: - self.remove_possible_simple_key() - token_number = self.tokens_taken+len(self.tokens) - key = SimpleKey(token_number, required, - self.index, self.line, self.column, self.get_mark()) - self.possible_simple_keys[self.flow_level] = key - - def remove_possible_simple_key(self): - # Remove the saved possible key position at the current flow level. - if self.flow_level in self.possible_simple_keys: - key = self.possible_simple_keys[self.flow_level] - - if key.required: - raise ScannerError("while scanning a simple key", key.mark, - "could not find expected ':'", self.get_mark()) - - del self.possible_simple_keys[self.flow_level] - - # Indentation functions. - - def unwind_indent(self, column): - - ## In flow context, tokens should respect indentation. - ## Actually the condition should be `self.indent >= column` according to - ## the spec. But this condition will prohibit intuitively correct - ## constructions such as - ## key : { - ## } - #if self.flow_level and self.indent > column: - # raise ScannerError(None, None, - # "invalid indentation or unclosed '[' or '{'", - # self.get_mark()) - - # In the flow context, indentation is ignored. We make the scanner less - # restrictive then specification requires. - if self.flow_level: - return - - # In block context, we may need to issue the BLOCK-END tokens. - while self.indent > column: - mark = self.get_mark() - self.indent = self.indents.pop() - self.tokens.append(BlockEndToken(mark, mark)) - - def add_indent(self, column): - # Check if we need to increase indentation. - if self.indent < column: - self.indents.append(self.indent) - self.indent = column - return True - return False - - # Fetchers. - - def fetch_stream_start(self): - # We always add STREAM-START as the first token and STREAM-END as the - # last token. - - # Read the token. - mark = self.get_mark() - - # Add STREAM-START. - self.tokens.append(StreamStartToken(mark, mark, - encoding=self.encoding)) - - - def fetch_stream_end(self): - - # Set the current indentation to -1. - self.unwind_indent(-1) - - # Reset simple keys. - self.remove_possible_simple_key() - self.allow_simple_key = False - self.possible_simple_keys = {} - - # Read the token. - mark = self.get_mark() - - # Add STREAM-END. - self.tokens.append(StreamEndToken(mark, mark)) - - # The steam is finished. - self.done = True - - def fetch_directive(self): - - # Set the current indentation to -1. - self.unwind_indent(-1) - - # Reset simple keys. - self.remove_possible_simple_key() - self.allow_simple_key = False - - # Scan and add DIRECTIVE. - self.tokens.append(self.scan_directive()) - - def fetch_document_start(self): - self.fetch_document_indicator(DocumentStartToken) - - def fetch_document_end(self): - self.fetch_document_indicator(DocumentEndToken) - - def fetch_document_indicator(self, TokenClass): - - # Set the current indentation to -1. - self.unwind_indent(-1) - - # Reset simple keys. Note that there could not be a block collection - # after '---'. - self.remove_possible_simple_key() - self.allow_simple_key = False - - # Add DOCUMENT-START or DOCUMENT-END. - start_mark = self.get_mark() - self.forward(3) - end_mark = self.get_mark() - self.tokens.append(TokenClass(start_mark, end_mark)) - - def fetch_flow_sequence_start(self): - self.fetch_flow_collection_start(FlowSequenceStartToken) - - def fetch_flow_mapping_start(self): - self.fetch_flow_collection_start(FlowMappingStartToken) - - def fetch_flow_collection_start(self, TokenClass): - - # '[' and '{' may start a simple key. - self.save_possible_simple_key() - - # Increase the flow level. - self.flow_level += 1 - - # Simple keys are allowed after '[' and '{'. - self.allow_simple_key = True - - # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START. - start_mark = self.get_mark() - self.forward() - end_mark = self.get_mark() - self.tokens.append(TokenClass(start_mark, end_mark)) - - def fetch_flow_sequence_end(self): - self.fetch_flow_collection_end(FlowSequenceEndToken) - - def fetch_flow_mapping_end(self): - self.fetch_flow_collection_end(FlowMappingEndToken) - - def fetch_flow_collection_end(self, TokenClass): - - # Reset possible simple key on the current level. - self.remove_possible_simple_key() - - # Decrease the flow level. - self.flow_level -= 1 - - # No simple keys after ']' or '}'. - self.allow_simple_key = False - - # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END. - start_mark = self.get_mark() - self.forward() - end_mark = self.get_mark() - self.tokens.append(TokenClass(start_mark, end_mark)) - - def fetch_flow_entry(self): - - # Simple keys are allowed after ','. - self.allow_simple_key = True - - # Reset possible simple key on the current level. - self.remove_possible_simple_key() - - # Add FLOW-ENTRY. - start_mark = self.get_mark() - self.forward() - end_mark = self.get_mark() - self.tokens.append(FlowEntryToken(start_mark, end_mark)) - - def fetch_block_entry(self): - - # Block context needs additional checks. - if not self.flow_level: - - # Are we allowed to start a new entry? - if not self.allow_simple_key: - raise ScannerError(None, None, - "sequence entries are not allowed here", - self.get_mark()) - - # We may need to add BLOCK-SEQUENCE-START. - if self.add_indent(self.column): - mark = self.get_mark() - self.tokens.append(BlockSequenceStartToken(mark, mark)) - - # It's an error for the block entry to occur in the flow context, - # but we let the parser detect this. - else: - pass - - # Simple keys are allowed after '-'. - self.allow_simple_key = True - - # Reset possible simple key on the current level. - self.remove_possible_simple_key() - - # Add BLOCK-ENTRY. - start_mark = self.get_mark() - self.forward() - end_mark = self.get_mark() - self.tokens.append(BlockEntryToken(start_mark, end_mark)) - - def fetch_key(self): - - # Block context needs additional checks. - if not self.flow_level: - - # Are we allowed to start a key (not necessary a simple)? - if not self.allow_simple_key: - raise ScannerError(None, None, - "mapping keys are not allowed here", - self.get_mark()) - - # We may need to add BLOCK-MAPPING-START. - if self.add_indent(self.column): - mark = self.get_mark() - self.tokens.append(BlockMappingStartToken(mark, mark)) - - # Simple keys are allowed after '?' in the block context. - self.allow_simple_key = not self.flow_level - - # Reset possible simple key on the current level. - self.remove_possible_simple_key() - - # Add KEY. - start_mark = self.get_mark() - self.forward() - end_mark = self.get_mark() - self.tokens.append(KeyToken(start_mark, end_mark)) - - def fetch_value(self): - - # Do we determine a simple key? - if self.flow_level in self.possible_simple_keys: - - # Add KEY. - key = self.possible_simple_keys[self.flow_level] - del self.possible_simple_keys[self.flow_level] - self.tokens.insert(key.token_number-self.tokens_taken, - KeyToken(key.mark, key.mark)) - - # If this key starts a new block mapping, we need to add - # BLOCK-MAPPING-START. - if not self.flow_level: - if self.add_indent(key.column): - self.tokens.insert(key.token_number-self.tokens_taken, - BlockMappingStartToken(key.mark, key.mark)) - - # There cannot be two simple keys one after another. - self.allow_simple_key = False - - # It must be a part of a complex key. - else: - - # Block context needs additional checks. - # (Do we really need them? They will be caught by the parser - # anyway.) - if not self.flow_level: - - # We are allowed to start a complex value if and only if - # we can start a simple key. - if not self.allow_simple_key: - raise ScannerError(None, None, - "mapping values are not allowed here", - self.get_mark()) - - # If this value starts a new block mapping, we need to add - # BLOCK-MAPPING-START. It will be detected as an error later by - # the parser. - if not self.flow_level: - if self.add_indent(self.column): - mark = self.get_mark() - self.tokens.append(BlockMappingStartToken(mark, mark)) - - # Simple keys are allowed after ':' in the block context. - self.allow_simple_key = not self.flow_level - - # Reset possible simple key on the current level. - self.remove_possible_simple_key() - - # Add VALUE. - start_mark = self.get_mark() - self.forward() - end_mark = self.get_mark() - self.tokens.append(ValueToken(start_mark, end_mark)) - - def fetch_alias(self): - - # ALIAS could be a simple key. - self.save_possible_simple_key() - - # No simple keys after ALIAS. - self.allow_simple_key = False - - # Scan and add ALIAS. - self.tokens.append(self.scan_anchor(AliasToken)) - - def fetch_anchor(self): - - # ANCHOR could start a simple key. - self.save_possible_simple_key() - - # No simple keys after ANCHOR. - self.allow_simple_key = False - - # Scan and add ANCHOR. - self.tokens.append(self.scan_anchor(AnchorToken)) - - def fetch_tag(self): - - # TAG could start a simple key. - self.save_possible_simple_key() - - # No simple keys after TAG. - self.allow_simple_key = False - - # Scan and add TAG. - self.tokens.append(self.scan_tag()) - - def fetch_literal(self): - self.fetch_block_scalar(style='|') - - def fetch_folded(self): - self.fetch_block_scalar(style='>') - - def fetch_block_scalar(self, style): - - # A simple key may follow a block scalar. - self.allow_simple_key = True - - # Reset possible simple key on the current level. - self.remove_possible_simple_key() - - # Scan and add SCALAR. - self.tokens.append(self.scan_block_scalar(style)) - - def fetch_single(self): - self.fetch_flow_scalar(style='\'') - - def fetch_double(self): - self.fetch_flow_scalar(style='"') - - def fetch_flow_scalar(self, style): - - # A flow scalar could be a simple key. - self.save_possible_simple_key() - - # No simple keys after flow scalars. - self.allow_simple_key = False - - # Scan and add SCALAR. - self.tokens.append(self.scan_flow_scalar(style)) - - def fetch_plain(self): - - # A plain scalar could be a simple key. - self.save_possible_simple_key() - - # No simple keys after plain scalars. But note that `scan_plain` will - # change this flag if the scan is finished at the beginning of the - # line. - self.allow_simple_key = False - - # Scan and add SCALAR. May change `allow_simple_key`. - self.tokens.append(self.scan_plain()) - - # Checkers. - - def check_directive(self): - - # DIRECTIVE: ^ '%' ... - # The '%' indicator is already checked. - if self.column == 0: - return True - - def check_document_start(self): - - # DOCUMENT-START: ^ '---' (' '|'\n') - if self.column == 0: - if self.prefix(3) == '---' \ - and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': - return True - - def check_document_end(self): - - # DOCUMENT-END: ^ '...' (' '|'\n') - if self.column == 0: - if self.prefix(3) == '...' \ - and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': - return True - - def check_block_entry(self): - - # BLOCK-ENTRY: '-' (' '|'\n') - return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' - - def check_key(self): - - # KEY(flow context): '?' - if self.flow_level: - return True - - # KEY(block context): '?' (' '|'\n') - else: - return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' - - def check_value(self): - - # VALUE(flow context): ':' - if self.flow_level: - return True - - # VALUE(block context): ':' (' '|'\n') - else: - return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' - - def check_plain(self): - - # A plain scalar may start with any non-space character except: - # '-', '?', ':', ',', '[', ']', '{', '}', - # '#', '&', '*', '!', '|', '>', '\'', '\"', - # '%', '@', '`'. - # - # It may also start with - # '-', '?', ':' - # if it is followed by a non-space character. - # - # Note that we limit the last rule to the block context (except the - # '-' character) because we want the flow context to be space - # independent. - ch = self.peek() - return ch not in '\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \ - or (self.peek(1) not in '\0 \t\r\n\x85\u2028\u2029' - and (ch == '-' or (not self.flow_level and ch in '?:'))) - - # Scanners. - - def scan_to_next_token(self): - # We ignore spaces, line breaks and comments. - # If we find a line break in the block context, we set the flag - # `allow_simple_key` on. - # The byte order mark is stripped if it's the first character in the - # stream. We do not yet support BOM inside the stream as the - # specification requires. Any such mark will be considered as a part - # of the document. - # - # TODO: We need to make tab handling rules more sane. A good rule is - # Tabs cannot precede tokens - # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END, - # KEY(block), VALUE(block), BLOCK-ENTRY - # So the checking code is - # if : - # self.allow_simple_keys = False - # We also need to add the check for `allow_simple_keys == True` to - # `unwind_indent` before issuing BLOCK-END. - # Scanners for block, flow, and plain scalars need to be modified. - - if self.index == 0 and self.peek() == '\uFEFF': - self.forward() - found = False - while not found: - while self.peek() == ' ': - self.forward() - if self.peek() == '#': - while self.peek() not in '\0\r\n\x85\u2028\u2029': - self.forward() - if self.scan_line_break(): - if not self.flow_level: - self.allow_simple_key = True - else: - found = True - - def scan_directive(self): - # See the specification for details. - start_mark = self.get_mark() - self.forward() - name = self.scan_directive_name(start_mark) - value = None - if name == 'YAML': - value = self.scan_yaml_directive_value(start_mark) - end_mark = self.get_mark() - elif name == 'TAG': - value = self.scan_tag_directive_value(start_mark) - end_mark = self.get_mark() - else: - end_mark = self.get_mark() - while self.peek() not in '\0\r\n\x85\u2028\u2029': - self.forward() - self.scan_directive_ignored_line(start_mark) - return DirectiveToken(name, value, start_mark, end_mark) - - def scan_directive_name(self, start_mark): - # See the specification for details. - length = 0 - ch = self.peek(length) - while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-_': - length += 1 - ch = self.peek(length) - if not length: - raise ScannerError("while scanning a directive", start_mark, - "expected alphabetic or numeric character, but found %r" - % ch, self.get_mark()) - value = self.prefix(length) - self.forward(length) - ch = self.peek() - if ch not in '\0 \r\n\x85\u2028\u2029': - raise ScannerError("while scanning a directive", start_mark, - "expected alphabetic or numeric character, but found %r" - % ch, self.get_mark()) - return value - - def scan_yaml_directive_value(self, start_mark): - # See the specification for details. - while self.peek() == ' ': - self.forward() - major = self.scan_yaml_directive_number(start_mark) - if self.peek() != '.': - raise ScannerError("while scanning a directive", start_mark, - "expected a digit or '.', but found %r" % self.peek(), - self.get_mark()) - self.forward() - minor = self.scan_yaml_directive_number(start_mark) - if self.peek() not in '\0 \r\n\x85\u2028\u2029': - raise ScannerError("while scanning a directive", start_mark, - "expected a digit or ' ', but found %r" % self.peek(), - self.get_mark()) - return (major, minor) - - def scan_yaml_directive_number(self, start_mark): - # See the specification for details. - ch = self.peek() - if not ('0' <= ch <= '9'): - raise ScannerError("while scanning a directive", start_mark, - "expected a digit, but found %r" % ch, self.get_mark()) - length = 0 - while '0' <= self.peek(length) <= '9': - length += 1 - value = int(self.prefix(length)) - self.forward(length) - return value - - def scan_tag_directive_value(self, start_mark): - # See the specification for details. - while self.peek() == ' ': - self.forward() - handle = self.scan_tag_directive_handle(start_mark) - while self.peek() == ' ': - self.forward() - prefix = self.scan_tag_directive_prefix(start_mark) - return (handle, prefix) - - def scan_tag_directive_handle(self, start_mark): - # See the specification for details. - value = self.scan_tag_handle('directive', start_mark) - ch = self.peek() - if ch != ' ': - raise ScannerError("while scanning a directive", start_mark, - "expected ' ', but found %r" % ch, self.get_mark()) - return value - - def scan_tag_directive_prefix(self, start_mark): - # See the specification for details. - value = self.scan_tag_uri('directive', start_mark) - ch = self.peek() - if ch not in '\0 \r\n\x85\u2028\u2029': - raise ScannerError("while scanning a directive", start_mark, - "expected ' ', but found %r" % ch, self.get_mark()) - return value - - def scan_directive_ignored_line(self, start_mark): - # See the specification for details. - while self.peek() == ' ': - self.forward() - if self.peek() == '#': - while self.peek() not in '\0\r\n\x85\u2028\u2029': - self.forward() - ch = self.peek() - if ch not in '\0\r\n\x85\u2028\u2029': - raise ScannerError("while scanning a directive", start_mark, - "expected a comment or a line break, but found %r" - % ch, self.get_mark()) - self.scan_line_break() - - def scan_anchor(self, TokenClass): - # The specification does not restrict characters for anchors and - # aliases. This may lead to problems, for instance, the document: - # [ *alias, value ] - # can be interpreted in two ways, as - # [ "value" ] - # and - # [ *alias , "value" ] - # Therefore we restrict aliases to numbers and ASCII letters. - start_mark = self.get_mark() - indicator = self.peek() - if indicator == '*': - name = 'alias' - else: - name = 'anchor' - self.forward() - length = 0 - ch = self.peek(length) - while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-_': - length += 1 - ch = self.peek(length) - if not length: - raise ScannerError("while scanning an %s" % name, start_mark, - "expected alphabetic or numeric character, but found %r" - % ch, self.get_mark()) - value = self.prefix(length) - self.forward(length) - ch = self.peek() - if ch not in '\0 \t\r\n\x85\u2028\u2029?:,]}%@`': - raise ScannerError("while scanning an %s" % name, start_mark, - "expected alphabetic or numeric character, but found %r" - % ch, self.get_mark()) - end_mark = self.get_mark() - return TokenClass(value, start_mark, end_mark) - - def scan_tag(self): - # See the specification for details. - start_mark = self.get_mark() - ch = self.peek(1) - if ch == '<': - handle = None - self.forward(2) - suffix = self.scan_tag_uri('tag', start_mark) - if self.peek() != '>': - raise ScannerError("while parsing a tag", start_mark, - "expected '>', but found %r" % self.peek(), - self.get_mark()) - self.forward() - elif ch in '\0 \t\r\n\x85\u2028\u2029': - handle = None - suffix = '!' - self.forward() - else: - length = 1 - use_handle = False - while ch not in '\0 \r\n\x85\u2028\u2029': - if ch == '!': - use_handle = True - break - length += 1 - ch = self.peek(length) - handle = '!' - if use_handle: - handle = self.scan_tag_handle('tag', start_mark) - else: - handle = '!' - self.forward() - suffix = self.scan_tag_uri('tag', start_mark) - ch = self.peek() - if ch not in '\0 \r\n\x85\u2028\u2029': - raise ScannerError("while scanning a tag", start_mark, - "expected ' ', but found %r" % ch, self.get_mark()) - value = (handle, suffix) - end_mark = self.get_mark() - return TagToken(value, start_mark, end_mark) - - def scan_block_scalar(self, style): - # See the specification for details. - - if style == '>': - folded = True - else: - folded = False - - chunks = [] - start_mark = self.get_mark() - - # Scan the header. - self.forward() - chomping, increment = self.scan_block_scalar_indicators(start_mark) - self.scan_block_scalar_ignored_line(start_mark) - - # Determine the indentation level and go to the first non-empty line. - min_indent = self.indent+1 - if min_indent < 1: - min_indent = 1 - if increment is None: - breaks, max_indent, end_mark = self.scan_block_scalar_indentation() - indent = max(min_indent, max_indent) - else: - indent = min_indent+increment-1 - breaks, end_mark = self.scan_block_scalar_breaks(indent) - line_break = '' - - # Scan the inner part of the block scalar. - while self.column == indent and self.peek() != '\0': - chunks.extend(breaks) - leading_non_space = self.peek() not in ' \t' - length = 0 - while self.peek(length) not in '\0\r\n\x85\u2028\u2029': - length += 1 - chunks.append(self.prefix(length)) - self.forward(length) - line_break = self.scan_line_break() - breaks, end_mark = self.scan_block_scalar_breaks(indent) - if self.column == indent and self.peek() != '\0': - - # Unfortunately, folding rules are ambiguous. - # - # This is the folding according to the specification: - - if folded and line_break == '\n' \ - and leading_non_space and self.peek() not in ' \t': - if not breaks: - chunks.append(' ') - else: - chunks.append(line_break) - - # This is Clark Evans's interpretation (also in the spec - # examples): - # - #if folded and line_break == '\n': - # if not breaks: - # if self.peek() not in ' \t': - # chunks.append(' ') - # else: - # chunks.append(line_break) - #else: - # chunks.append(line_break) - else: - break - - # Chomp the tail. - if chomping is not False: - chunks.append(line_break) - if chomping is True: - chunks.extend(breaks) - - # We are done. - return ScalarToken(''.join(chunks), False, start_mark, end_mark, - style) - - def scan_block_scalar_indicators(self, start_mark): - # See the specification for details. - chomping = None - increment = None - ch = self.peek() - if ch in '+-': - if ch == '+': - chomping = True - else: - chomping = False - self.forward() - ch = self.peek() - if ch in '0123456789': - increment = int(ch) - if increment == 0: - raise ScannerError("while scanning a block scalar", start_mark, - "expected indentation indicator in the range 1-9, but found 0", - self.get_mark()) - self.forward() - elif ch in '0123456789': - increment = int(ch) - if increment == 0: - raise ScannerError("while scanning a block scalar", start_mark, - "expected indentation indicator in the range 1-9, but found 0", - self.get_mark()) - self.forward() - ch = self.peek() - if ch in '+-': - if ch == '+': - chomping = True - else: - chomping = False - self.forward() - ch = self.peek() - if ch not in '\0 \r\n\x85\u2028\u2029': - raise ScannerError("while scanning a block scalar", start_mark, - "expected chomping or indentation indicators, but found %r" - % ch, self.get_mark()) - return chomping, increment - - def scan_block_scalar_ignored_line(self, start_mark): - # See the specification for details. - while self.peek() == ' ': - self.forward() - if self.peek() == '#': - while self.peek() not in '\0\r\n\x85\u2028\u2029': - self.forward() - ch = self.peek() - if ch not in '\0\r\n\x85\u2028\u2029': - raise ScannerError("while scanning a block scalar", start_mark, - "expected a comment or a line break, but found %r" % ch, - self.get_mark()) - self.scan_line_break() - - def scan_block_scalar_indentation(self): - # See the specification for details. - chunks = [] - max_indent = 0 - end_mark = self.get_mark() - while self.peek() in ' \r\n\x85\u2028\u2029': - if self.peek() != ' ': - chunks.append(self.scan_line_break()) - end_mark = self.get_mark() - else: - self.forward() - if self.column > max_indent: - max_indent = self.column - return chunks, max_indent, end_mark - - def scan_block_scalar_breaks(self, indent): - # See the specification for details. - chunks = [] - end_mark = self.get_mark() - while self.column < indent and self.peek() == ' ': - self.forward() - while self.peek() in '\r\n\x85\u2028\u2029': - chunks.append(self.scan_line_break()) - end_mark = self.get_mark() - while self.column < indent and self.peek() == ' ': - self.forward() - return chunks, end_mark - - def scan_flow_scalar(self, style): - # See the specification for details. - # Note that we loose indentation rules for quoted scalars. Quoted - # scalars don't need to adhere indentation because " and ' clearly - # mark the beginning and the end of them. Therefore we are less - # restrictive then the specification requires. We only need to check - # that document separators are not included in scalars. - if style == '"': - double = True - else: - double = False - chunks = [] - start_mark = self.get_mark() - quote = self.peek() - self.forward() - chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) - while self.peek() != quote: - chunks.extend(self.scan_flow_scalar_spaces(double, start_mark)) - chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) - self.forward() - end_mark = self.get_mark() - return ScalarToken(''.join(chunks), False, start_mark, end_mark, - style) - - ESCAPE_REPLACEMENTS = { - '0': '\0', - 'a': '\x07', - 'b': '\x08', - 't': '\x09', - '\t': '\x09', - 'n': '\x0A', - 'v': '\x0B', - 'f': '\x0C', - 'r': '\x0D', - 'e': '\x1B', - ' ': '\x20', - '\"': '\"', - '\\': '\\', - '/': '/', - 'N': '\x85', - '_': '\xA0', - 'L': '\u2028', - 'P': '\u2029', - } - - ESCAPE_CODES = { - 'x': 2, - 'u': 4, - 'U': 8, - } - - def scan_flow_scalar_non_spaces(self, double, start_mark): - # See the specification for details. - chunks = [] - while True: - length = 0 - while self.peek(length) not in '\'\"\\\0 \t\r\n\x85\u2028\u2029': - length += 1 - if length: - chunks.append(self.prefix(length)) - self.forward(length) - ch = self.peek() - if not double and ch == '\'' and self.peek(1) == '\'': - chunks.append('\'') - self.forward(2) - elif (double and ch == '\'') or (not double and ch in '\"\\'): - chunks.append(ch) - self.forward() - elif double and ch == '\\': - self.forward() - ch = self.peek() - if ch in self.ESCAPE_REPLACEMENTS: - chunks.append(self.ESCAPE_REPLACEMENTS[ch]) - self.forward() - elif ch in self.ESCAPE_CODES: - length = self.ESCAPE_CODES[ch] - self.forward() - for k in range(length): - if self.peek(k) not in '0123456789ABCDEFabcdef': - raise ScannerError("while scanning a double-quoted scalar", start_mark, - "expected escape sequence of %d hexdecimal numbers, but found %r" % - (length, self.peek(k)), self.get_mark()) - code = int(self.prefix(length), 16) - chunks.append(chr(code)) - self.forward(length) - elif ch in '\r\n\x85\u2028\u2029': - self.scan_line_break() - chunks.extend(self.scan_flow_scalar_breaks(double, start_mark)) - else: - raise ScannerError("while scanning a double-quoted scalar", start_mark, - "found unknown escape character %r" % ch, self.get_mark()) - else: - return chunks - - def scan_flow_scalar_spaces(self, double, start_mark): - # See the specification for details. - chunks = [] - length = 0 - while self.peek(length) in ' \t': - length += 1 - whitespaces = self.prefix(length) - self.forward(length) - ch = self.peek() - if ch == '\0': - raise ScannerError("while scanning a quoted scalar", start_mark, - "found unexpected end of stream", self.get_mark()) - elif ch in '\r\n\x85\u2028\u2029': - line_break = self.scan_line_break() - breaks = self.scan_flow_scalar_breaks(double, start_mark) - if line_break != '\n': - chunks.append(line_break) - elif not breaks: - chunks.append(' ') - chunks.extend(breaks) - else: - chunks.append(whitespaces) - return chunks - - def scan_flow_scalar_breaks(self, double, start_mark): - # See the specification for details. - chunks = [] - while True: - # Instead of checking indentation, we check for document - # separators. - prefix = self.prefix(3) - if (prefix == '---' or prefix == '...') \ - and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': - raise ScannerError("while scanning a quoted scalar", start_mark, - "found unexpected document separator", self.get_mark()) - while self.peek() in ' \t': - self.forward() - if self.peek() in '\r\n\x85\u2028\u2029': - chunks.append(self.scan_line_break()) - else: - return chunks - - def scan_plain(self): - # See the specification for details. - # We add an additional restriction for the flow context: - # plain scalars in the flow context cannot contain ',' or '?'. - # We also keep track of the `allow_simple_key` flag here. - # Indentation rules are loosed for the flow context. - chunks = [] - start_mark = self.get_mark() - end_mark = start_mark - indent = self.indent+1 - # We allow zero indentation for scalars, but then we need to check for - # document separators at the beginning of the line. - #if indent == 0: - # indent = 1 - spaces = [] - while True: - length = 0 - if self.peek() == '#': - break - while True: - ch = self.peek(length) - if ch in '\0 \t\r\n\x85\u2028\u2029' \ - or (ch == ':' and - self.peek(length+1) in '\0 \t\r\n\x85\u2028\u2029' - + (u',[]{}' if self.flow_level else u''))\ - or (self.flow_level and ch in ',?[]{}'): - break - length += 1 - if length == 0: - break - self.allow_simple_key = False - chunks.extend(spaces) - chunks.append(self.prefix(length)) - self.forward(length) - end_mark = self.get_mark() - spaces = self.scan_plain_spaces(indent, start_mark) - if not spaces or self.peek() == '#' \ - or (not self.flow_level and self.column < indent): - break - return ScalarToken(''.join(chunks), True, start_mark, end_mark) - - def scan_plain_spaces(self, indent, start_mark): - # See the specification for details. - # The specification is really confusing about tabs in plain scalars. - # We just forbid them completely. Do not use tabs in YAML! - chunks = [] - length = 0 - while self.peek(length) in ' ': - length += 1 - whitespaces = self.prefix(length) - self.forward(length) - ch = self.peek() - if ch in '\r\n\x85\u2028\u2029': - line_break = self.scan_line_break() - self.allow_simple_key = True - prefix = self.prefix(3) - if (prefix == '---' or prefix == '...') \ - and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': - return - breaks = [] - while self.peek() in ' \r\n\x85\u2028\u2029': - if self.peek() == ' ': - self.forward() - else: - breaks.append(self.scan_line_break()) - prefix = self.prefix(3) - if (prefix == '---' or prefix == '...') \ - and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': - return - if line_break != '\n': - chunks.append(line_break) - elif not breaks: - chunks.append(' ') - chunks.extend(breaks) - elif whitespaces: - chunks.append(whitespaces) - return chunks - - def scan_tag_handle(self, name, start_mark): - # See the specification for details. - # For some strange reasons, the specification does not allow '_' in - # tag handles. I have allowed it anyway. - ch = self.peek() - if ch != '!': - raise ScannerError("while scanning a %s" % name, start_mark, - "expected '!', but found %r" % ch, self.get_mark()) - length = 1 - ch = self.peek(length) - if ch != ' ': - while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-_': - length += 1 - ch = self.peek(length) - if ch != '!': - self.forward(length) - raise ScannerError("while scanning a %s" % name, start_mark, - "expected '!', but found %r" % ch, self.get_mark()) - length += 1 - value = self.prefix(length) - self.forward(length) - return value - - def scan_tag_uri(self, name, start_mark): - # See the specification for details. - # Note: we do not check if URI is well-formed. - chunks = [] - length = 0 - ch = self.peek(length) - while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ - or ch in '-;/?:@&=+$,_.!~*\'()[]%': - if ch == '%': - chunks.append(self.prefix(length)) - self.forward(length) - length = 0 - chunks.append(self.scan_uri_escapes(name, start_mark)) - else: - length += 1 - ch = self.peek(length) - if length: - chunks.append(self.prefix(length)) - self.forward(length) - length = 0 - if not chunks: - raise ScannerError("while parsing a %s" % name, start_mark, - "expected URI, but found %r" % ch, self.get_mark()) - return ''.join(chunks) - - def scan_uri_escapes(self, name, start_mark): - # See the specification for details. - codes = [] - mark = self.get_mark() - while self.peek() == '%': - self.forward() - for k in range(2): - if self.peek(k) not in '0123456789ABCDEFabcdef': - raise ScannerError("while scanning a %s" % name, start_mark, - "expected URI escape sequence of 2 hexdecimal numbers, but found %r" - % self.peek(k), self.get_mark()) - codes.append(int(self.prefix(2), 16)) - self.forward(2) - try: - value = bytes(codes).decode('utf-8') - except UnicodeDecodeError as exc: - raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark) - return value - - def scan_line_break(self): - # Transforms: - # '\r\n' : '\n' - # '\r' : '\n' - # '\n' : '\n' - # '\x85' : '\n' - # '\u2028' : '\u2028' - # '\u2029 : '\u2029' - # default : '' - ch = self.peek() - if ch in '\r\n\x85': - if self.prefix(2) == '\r\n': - self.forward(2) - else: - self.forward() - return '\n' - elif ch in '\u2028\u2029': - self.forward() - return ch - return '' diff --git a/src/yaml/serializer.py b/src/yaml/serializer.py deleted file mode 100644 index fe911e6..0000000 --- a/src/yaml/serializer.py +++ /dev/null @@ -1,111 +0,0 @@ - -__all__ = ['Serializer', 'SerializerError'] - -from .error import YAMLError -from .events import * -from .nodes import * - -class SerializerError(YAMLError): - pass - -class Serializer: - - ANCHOR_TEMPLATE = 'id%03d' - - def __init__(self, encoding=None, - explicit_start=None, explicit_end=None, version=None, tags=None): - self.use_encoding = encoding - self.use_explicit_start = explicit_start - self.use_explicit_end = explicit_end - self.use_version = version - self.use_tags = tags - self.serialized_nodes = {} - self.anchors = {} - self.last_anchor_id = 0 - self.closed = None - - def open(self): - if self.closed is None: - self.emit(StreamStartEvent(encoding=self.use_encoding)) - self.closed = False - elif self.closed: - raise SerializerError("serializer is closed") - else: - raise SerializerError("serializer is already opened") - - def close(self): - if self.closed is None: - raise SerializerError("serializer is not opened") - elif not self.closed: - self.emit(StreamEndEvent()) - self.closed = True - - #def __del__(self): - # self.close() - - def serialize(self, node): - if self.closed is None: - raise SerializerError("serializer is not opened") - elif self.closed: - raise SerializerError("serializer is closed") - self.emit(DocumentStartEvent(explicit=self.use_explicit_start, - version=self.use_version, tags=self.use_tags)) - self.anchor_node(node) - self.serialize_node(node, None, None) - self.emit(DocumentEndEvent(explicit=self.use_explicit_end)) - self.serialized_nodes = {} - self.anchors = {} - self.last_anchor_id = 0 - - def anchor_node(self, node): - if node in self.anchors: - if self.anchors[node] is None: - self.anchors[node] = self.generate_anchor(node) - else: - self.anchors[node] = None - if isinstance(node, SequenceNode): - for item in node.value: - self.anchor_node(item) - elif isinstance(node, MappingNode): - for key, value in node.value: - self.anchor_node(key) - self.anchor_node(value) - - def generate_anchor(self, node): - self.last_anchor_id += 1 - return self.ANCHOR_TEMPLATE % self.last_anchor_id - - def serialize_node(self, node, parent, index): - alias = self.anchors[node] - if node in self.serialized_nodes: - self.emit(AliasEvent(alias)) - else: - self.serialized_nodes[node] = True - self.descend_resolver(parent, index) - if isinstance(node, ScalarNode): - detected_tag = self.resolve(ScalarNode, node.value, (True, False)) - default_tag = self.resolve(ScalarNode, node.value, (False, True)) - implicit = (node.tag == detected_tag), (node.tag == default_tag) - self.emit(ScalarEvent(alias, node.tag, implicit, node.value, - style=node.style)) - elif isinstance(node, SequenceNode): - implicit = (node.tag - == self.resolve(SequenceNode, node.value, True)) - self.emit(SequenceStartEvent(alias, node.tag, implicit, - flow_style=node.flow_style)) - index = 0 - for item in node.value: - self.serialize_node(item, node, index) - index += 1 - self.emit(SequenceEndEvent()) - elif isinstance(node, MappingNode): - implicit = (node.tag - == self.resolve(MappingNode, node.value, True)) - self.emit(MappingStartEvent(alias, node.tag, implicit, - flow_style=node.flow_style)) - for key, value in node.value: - self.serialize_node(key, node, None) - self.serialize_node(value, node, key) - self.emit(MappingEndEvent()) - self.ascend_resolver() - diff --git a/src/yaml/tokens.py b/src/yaml/tokens.py deleted file mode 100644 index 4d0b48a..0000000 --- a/src/yaml/tokens.py +++ /dev/null @@ -1,104 +0,0 @@ - -class Token(object): - def __init__(self, start_mark, end_mark): - self.start_mark = start_mark - self.end_mark = end_mark - def __repr__(self): - attributes = [key for key in self.__dict__ - if not key.endswith('_mark')] - attributes.sort() - arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) - for key in attributes]) - return '%s(%s)' % (self.__class__.__name__, arguments) - -#class BOMToken(Token): -# id = '' - -class DirectiveToken(Token): - id = '' - def __init__(self, name, value, start_mark, end_mark): - self.name = name - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - -class DocumentStartToken(Token): - id = '' - -class DocumentEndToken(Token): - id = '' - -class StreamStartToken(Token): - id = '' - def __init__(self, start_mark=None, end_mark=None, - encoding=None): - self.start_mark = start_mark - self.end_mark = end_mark - self.encoding = encoding - -class StreamEndToken(Token): - id = '' - -class BlockSequenceStartToken(Token): - id = '' - -class BlockMappingStartToken(Token): - id = '' - -class BlockEndToken(Token): - id = '' - -class FlowSequenceStartToken(Token): - id = '[' - -class FlowMappingStartToken(Token): - id = '{' - -class FlowSequenceEndToken(Token): - id = ']' - -class FlowMappingEndToken(Token): - id = '}' - -class KeyToken(Token): - id = '?' - -class ValueToken(Token): - id = ':' - -class BlockEntryToken(Token): - id = '-' - -class FlowEntryToken(Token): - id = ',' - -class AliasToken(Token): - id = '' - def __init__(self, value, start_mark, end_mark): - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - -class AnchorToken(Token): - id = '' - def __init__(self, value, start_mark, end_mark): - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - -class TagToken(Token): - id = '' - def __init__(self, value, start_mark, end_mark): - self.value = value - self.start_mark = start_mark - self.end_mark = end_mark - -class ScalarToken(Token): - id = '' - def __init__(self, value, plain, start_mark, end_mark, style=None): - self.value = value - self.plain = plain - self.start_mark = start_mark - self.end_mark = end_mark - self.style = style - From 9af391ff9de63f30eb9709ac2d177390dc54ed2d Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Wed, 24 Jun 2020 20:08:53 +0200 Subject: [PATCH 03/12] clean up imports, cmdline handling Order imports properly. Fix path when running script directly from repo rather than as an installed package. Refactor command line handling. --- src/wireviz/wireviz.py | 38 +++++++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 11 deletions(-) diff --git a/src/wireviz/wireviz.py b/src/wireviz/wireviz.py index ceb350a..70fb85f 100755 --- a/src/wireviz/wireviz.py +++ b/src/wireviz/wireviz.py @@ -1,12 +1,16 @@ #!/usr/bin/env python3 import argparse -import os -from dataclasses import dataclass, field -from typing import Any, List from collections import Counter -import yaml +from dataclasses import dataclass, field from graphviz import Graph +import os +from typing import Any, List +import yaml + +if __name__== '__main__': + import sys + sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..')) from wireviz import wv_colors from wireviz.wv_helper import nested, int2tuple, awg_equiv, flatten2d, tuplelist2tsv @@ -622,14 +626,26 @@ def parse(file_in, file_out=None, gen_bom=False): h.output(filename=file_out, format=('png','svg'), gen_bom=gen_bom, view=False) -def main(): - ap = argparse.ArgumentParser() - ap.add_argument('file_input', nargs='?', default='_test/test.yml') - ap.add_argument('file_output', nargs='?', default=None) - ap.add_argument('--bom', action='store_const', default=True, const=True) - args = ap.parse_args() +def parse_cmdline(): + parser = argparse.ArgumentParser( + description='Generate cable and wiring harness documentation from YAML descriptions' + ) - parse(args.file_input, file_out=args.file_output, gen_bom=args.bom) + parser.add_argument('input_file', action='store', type=str, metavar='YAML_FILE') + + parser.add_argument('-o', '--output_file', action='store', type=str, metavar='OUTPUT') + + parser.add_argument('--generate-bom', action='store_true', default=True) + + args = parser.parse_args() + + return args + +def main(): + + args = parse_cmdline() + + parse(args.input_file, file_out=args.output_file, gen_bom=args.generate_bom) if __name__ == '__main__': main() From 60cd069754d8dab702568ec6bcf9fbdad06c3982 Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Wed, 24 Jun 2020 18:52:25 +0200 Subject: [PATCH 04/12] add install instructions to readme --- README.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/README.md b/README.md index df7092a..0ec6f6b 100644 --- a/README.md +++ b/README.md @@ -24,6 +24,16 @@ WireViz is a tool for easily documenting cables, wiring harnesses and connector _Note_: WireViz is not designed to represent the complete wiring of a system. Its main aim is to document the construction of individual wires and harnesses. +## Installation + +Installation can be done using pip after cloning the repository: + +``` +git clone +cd +pip3 install -e . +``` + ## Examples ### Demo 01 From cdb2cf2b91fd2f3c6edf39e10a48de6751766dc4 Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Wed, 24 Jun 2020 19:09:08 +0200 Subject: [PATCH 05/12] update build_examples script --- README.md | 8 ++++++ src/wireviz/batch.py | 50 ----------------------------------- src/wireviz/build_examples.py | 26 +++++++++--------- 3 files changed, 22 insertions(+), 62 deletions(-) delete mode 100644 src/wireviz/batch.py mode change 100644 => 100755 src/wireviz/build_examples.py diff --git a/README.md b/README.md index 0ec6f6b..3f90415 100644 --- a/README.md +++ b/README.md @@ -36,6 +36,14 @@ pip3 install -e . ## Examples +### (re)building the example projects + +If you would like to rebuild all of the included demos, examples and tutorials, use the ```build_examples.py``` script: + +```cd src/wireviz +./build_examples.py +``` + ### Demo 01 [WireViz input file](examples/demo01.yml): diff --git a/src/wireviz/batch.py b/src/wireviz/batch.py deleted file mode 100644 index 6add6a9..0000000 --- a/src/wireviz/batch.py +++ /dev/null @@ -1,50 +0,0 @@ -import wireviz -import os - -demos = 2 # 2 -examples = 9 # 9 -tutorials = 7 # 7 - -if demos: - for i in range(1,demos+1): - fn = '../examples/demo{:02d}.yml'.format(i) - print(fn) - wireviz.parse(fn, gen_bom=True) - -if examples: - with open(os.path.abspath('../examples/readme.md'), 'w') as file: - file.write('# Example gallery\n') - for i in range(1,examples+1): - fn = '../examples/ex{:02d}.yml'.format(i) - print(fn) - wireviz.parse(fn, gen_bom=True) - - file.write('## Example {:02d}\n'.format(i)) - file.write('![](ex{:02d}.png)\n\n'.format(i)) - file.write('[Source](ex{:02d}.yml) - [Bill of Materials](ex{:02d}.bom.tsv)\n\n\n'.format(i,i)) - -if tutorials: - with open(os.path.abspath('../tutorial/readme.md'), 'w') as file: - file.write('# WireViz Tutorial\n') - for i in range(1,tutorials+1): - fn = '../tutorial/tutorial{:02d}.yml'.format(i) - print(fn) - wireviz.parse(fn, gen_bom=True) - - with open(os.path.abspath('../tutorial/tutorial{:02d}.md'.format(i)), 'r') as info: - for line in info: - file.write(line.replace('## ', '## {} - '.format(i))) - file.write('\n[Source](tutorial{:02d}.yml):\n\n'.format(i)) - - with open(os.path.abspath('../tutorial/tutorial{:02d}.yml'.format(i)), 'r') as src: - file.write('```yaml\n') - for line in src: - file.write(line) - file.write('```\n') - file.write('\n') - - file.write('\nOutput:\n\n'.format(i)) - - file.write('![](tutorial{:02d}.png)\n\n'.format(i)) - - file.write('[Bill of Materials](tutorial{:02d}.bom.tsv)\n\n\n'.format(i)) diff --git a/src/wireviz/build_examples.py b/src/wireviz/build_examples.py old mode 100644 new mode 100755 index d989ae1..8d8afbc --- a/src/wireviz/build_examples.py +++ b/src/wireviz/build_examples.py @@ -1,25 +1,27 @@ -import wireviz +#!/usr/bin/python3 + import os +import sys + +sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..')) + +from wireviz import wireviz demos = 2 # 2 -<<<<<<< HEAD:src/wireviz/batch.py examples = 9 # 9 -======= -examples = 6 # 6 ->>>>>>> 2d428e8... refactor dependencies and installation:src/wireviz/build_examples.py tutorials = 7 # 7 if demos: for i in range(1,demos+1): - fn = '../examples/demo{:02d}.yml'.format(i) + fn = '../../examples/demo{:02d}.yml'.format(i) print(fn) wireviz.parse(fn, gen_bom=True) if examples: - with open(os.path.abspath('../examples/readme.md'), 'w') as file: + with open(os.path.abspath('../../examples/readme.md'), 'w') as file: file.write('# Example gallery\n') for i in range(1,examples+1): - fn = '../examples/ex{:02d}.yml'.format(i) + fn = '../../examples/ex{:02d}.yml'.format(i) print(fn) wireviz.parse(fn, gen_bom=True) @@ -28,19 +30,19 @@ if examples: file.write('[Source](ex{:02d}.yml) - [Bill of Materials](ex{:02d}.bom.tsv)\n\n\n'.format(i,i)) if tutorials: - with open(os.path.abspath('../tutorial/readme.md'), 'w') as file: + with open(os.path.abspath('../../tutorial/readme.md'), 'w') as file: file.write('# WireViz Tutorial\n') for i in range(1,tutorials+1): - fn = '../tutorial/tutorial{:02d}.yml'.format(i) + fn = '../../tutorial/tutorial{:02d}.yml'.format(i) print(fn) wireviz.parse(fn, gen_bom=True) - with open(os.path.abspath('../tutorial/tutorial{:02d}.md'.format(i)), 'r') as info: + with open(os.path.abspath('../../tutorial/tutorial{:02d}.md'.format(i)), 'r') as info: for line in info: file.write(line.replace('## ', '## {} - '.format(i))) file.write('\n[Source](tutorial{:02d}.yml):\n\n'.format(i)) - with open(os.path.abspath('../tutorial/tutorial{:02d}.yml'.format(i)), 'r') as src: + with open(os.path.abspath('../../tutorial/tutorial{:02d}.yml'.format(i)), 'r') as src: file.write('```yaml\n') for line in src: file.write(line) From 668667d4fe4e1cd4ad873910a0cd11b4bafdda38 Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Wed, 24 Jun 2020 17:14:25 +0200 Subject: [PATCH 06/12] Fix typo --- TODO | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/TODO b/TODO index dc40abd..619e1ec 100644 --- a/TODO +++ b/TODO @@ -35,7 +35,7 @@ ## Other -* Imrpove tutorial texts +* Improve tutorial texts * Create syntax reference / cheat sheet * Set global parameters (show_pins, ...) and allow override on per-item basis * Allow custom GraphViz code before/after WireViz-generated code From a1f511738e7b3e810ff388d062c46bb6a8eae167 Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Thu, 25 Jun 2020 11:34:58 +0200 Subject: [PATCH 07/12] fix install notes Explicitly mention the system graphviz dependency and clarify possible need for separate python install on old ubuntus --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 3f90415..8b2dc48 100644 --- a/README.md +++ b/README.md @@ -26,7 +26,9 @@ _Note_: WireViz is not designed to represent the complete wiring of a system. It ## Installation -Installation can be done using pip after cloning the repository: +WireWiz requires the ```graphviz``` package as well as it's python bindings. Graphviz itself is installed using your regular package manager, e.g. ```apt-get install graphviz```. The Graphviz python bindings are automatically installed as dependencies by the install script. + +Installation of the WireWiz package and its python dependencies can be done using pip after cloning the repository: ``` git clone @@ -97,7 +99,7 @@ as well as the [example gallery](examples/readme.md) to see more of what WireViz ## Usage ``` -$ python3 wireviz.py ~/path/to/file/mywire.yml +$ wireviz ~/path/to/file/mywire.yml ``` This will output the following files @@ -116,7 +118,7 @@ This is very much a [work in progress](TODO). Source code, API, syntax and funct ## Requirements -Developed and tested using Python 3.7; might not work with older Python versions. +Developed and tested using Python 3.7; might not work with older Python versions. Ubuntu 18.04 LTS users in particular may need to separately install Python 3.7 or above, as that comes with Python 3.6 as the included system Python install. ## License From f14a07fe95c21e85e3de3e5e96f7796378b8e684 Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Thu, 25 Jun 2020 13:34:46 +0200 Subject: [PATCH 08/12] feature: add --prepend-file option - Allow prepending a separate YAML file for e.g. including common template definitions. This is accomodated by a new commandline option, --prepend-file, which takes a path to a YAML file. This is prepended to the regular input as-is. - Refactor file loading to accomodate the above. This includes moving relevant parts to main() and instead supplying parse () with a string representation of the YAML data. Also add early file existance checks and bail out if any of the inputs are inaccessible or nonexistant. --- src/wireviz/wireviz.py | 43 +++++++++++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 13 deletions(-) diff --git a/src/wireviz/wireviz.py b/src/wireviz/wireviz.py index 70fb85f..af37544 100755 --- a/src/wireviz/wireviz.py +++ b/src/wireviz/wireviz.py @@ -5,11 +5,11 @@ from collections import Counter from dataclasses import dataclass, field from graphviz import Graph import os +import sys from typing import Any, List import yaml if __name__== '__main__': - import sys sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..')) from wireviz import wv_colors @@ -448,17 +448,9 @@ class Connection: to_name: Any to_port: Any -def parse(file_in, file_out=None, gen_bom=False): +def parse(yaml_input, file_out=None, generate_bom=False): - file_in = os.path.abspath(file_in) - if not file_out: - file_out = file_in - pre, ext = os.path.splitext(file_out) - file_out = pre # extension will be added by graphviz output function - file_out = os.path.abspath(file_out) - - with open(file_in, 'r') as stream: - input = yaml.safe_load(stream) + input = yaml.safe_load(yaml_input) def expand(input): # input can be: @@ -624,7 +616,7 @@ def parse(file_in, file_out=None, gen_bom=False): else: raise Exception('Wrong number of connection parameters') - h.output(filename=file_out, format=('png','svg'), gen_bom=gen_bom, view=False) + h.output(filename=file_out, format=('png','svg'), gen_bom=generate_bom, view=False) def parse_cmdline(): parser = argparse.ArgumentParser( @@ -637,6 +629,8 @@ def parse_cmdline(): parser.add_argument('--generate-bom', action='store_true', default=True) + parser.add_argument('--prepend-file', action='store', type=str, metavar='YAML_FILE') + args = parser.parse_args() return args @@ -645,7 +639,30 @@ def main(): args = parse_cmdline() - parse(args.input_file, file_out=args.output_file, gen_bom=args.generate_bom) + if not os.path.exists(args.input_file): + print('Error: input file {} inaccessible or does not exist, check path'.format(args.input_file)) + sys.exit(1) + + with open(args.input_file) as fh: + yaml_input = fh.read() + + if args.prepend_file: + if not os.path.exists(args.prepend_file): + print('Error: prepend input file {} inaccessible or does not exist, check path'.format(args.prepend_file)) + sys.exit(1) + with open(args.prepend_file) as fh: + prepend = fh.read() + yaml_input = prepend + yaml_input + + if not args.output_file: + file_out = args.input_file + pre, _ = os.path.splitext(file_out) + file_out = pre # extension will be added by graphviz output function + else: + file_out = args.output_file + file_out = os.path.abspath(file_out) + + parse(yaml_input, file_out=file_out, generate_bom=args.generate_bom) if __name__ == '__main__': main() From 1f06c6017c4c33661fe5429ebaa6222e04c423e7 Mon Sep 17 00:00:00 2001 From: Andreas Nordin Date: Thu, 25 Jun 2020 13:41:00 +0200 Subject: [PATCH 09/12] refactor: rename 'input' -> 'yaml_data' 'input' overloads a python built-in name. Refactor to avoid this. --- src/wireviz/wireviz.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/src/wireviz/wireviz.py b/src/wireviz/wireviz.py index af37544..fddbdd1 100755 --- a/src/wireviz/wireviz.py +++ b/src/wireviz/wireviz.py @@ -450,17 +450,17 @@ class Connection: def parse(yaml_input, file_out=None, generate_bom=False): - input = yaml.safe_load(yaml_input) + yaml_data = yaml.safe_load(yaml_input) - def expand(input): - # input can be: + def expand(yaml_data): + # yaml_data can be: # - a singleton (normally str or int) # - a list of str or int # if str is of the format '#-#', it is treated as a range (inclusive) and expanded output = [] - if not isinstance(input, list): - input = [input,] - for e in input: + if not isinstance(yaml_data, list): + yaml_data = [yaml_data,] + for e in yaml_data: e = str(e) if '-' in e: # list of pins a, b = tuple(map(int, e.split('-'))) @@ -482,7 +482,7 @@ def parse(yaml_input, file_out=None, generate_bom=False): def check_designators(what, where): for i, x in enumerate(what): - if x not in input[where[i]]: + if x not in yaml_data[where[i]]: return False return True @@ -492,10 +492,10 @@ def parse(yaml_input, file_out=None, generate_bom=False): sections = ['connectors','cables','ferrules','connections'] types = [dict, dict, dict, list] for sec, ty in zip(sections, types): - if sec in input and type(input[sec]) == ty: - if len(input[sec]) > 0: + if sec in yaml_data and type(yaml_data[sec]) == ty: + if len(yaml_data[sec]) > 0: if ty == dict: - for k, o in input[sec].items(): + for k, o in yaml_data[sec].items(): if sec == 'connectors': h.add_connector(name=k, **o) elif sec == 'cables': @@ -506,13 +506,13 @@ def parse(yaml_input, file_out=None, generate_bom=False): pass # section exists but is empty else: # section does not exist, create empty section if ty == dict: - input[sec] = {} + yaml_data[sec] = {} elif ty == list: - input[sec] = [] + yaml_data[sec] = [] # add connections ferrule_counter = 0 - for con in input['connections']: + for con in yaml_data['connections']: if len(con) == 3: # format: connector -- cable -- conector for c in con: @@ -601,7 +601,7 @@ def parse(yaml_input, file_out=None, generate_bom=False): cable_name = from_name cable_pins = from_pins - ferrule_params = input['ferrules'][ferrule_name] + ferrule_params = yaml_data['ferrules'][ferrule_name] for cable_pin in cable_pins: ferrule_counter = ferrule_counter + 1 ferrule_id = '_F{}'.format(ferrule_counter) From 154e28f257ec837e5c13de8a6075adf3f0fd7e6d Mon Sep 17 00:00:00 2001 From: Daniel Rojas Date: Sun, 28 Jun 2020 11:43:22 +0200 Subject: [PATCH 10/12] Change gen_bom to generate_bom --- src/wireviz/build_examples.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/wireviz/build_examples.py b/src/wireviz/build_examples.py index 8d8afbc..b7be539 100755 --- a/src/wireviz/build_examples.py +++ b/src/wireviz/build_examples.py @@ -15,7 +15,7 @@ if demos: for i in range(1,demos+1): fn = '../../examples/demo{:02d}.yml'.format(i) print(fn) - wireviz.parse(fn, gen_bom=True) + wireviz.parse(fn, generate_bom=True) if examples: with open(os.path.abspath('../../examples/readme.md'), 'w') as file: @@ -23,7 +23,7 @@ if examples: for i in range(1,examples+1): fn = '../../examples/ex{:02d}.yml'.format(i) print(fn) - wireviz.parse(fn, gen_bom=True) + wireviz.parse(fn, generate_bom=True) file.write('## Example {:02d}\n'.format(i)) file.write('![](ex{:02d}.png)\n\n'.format(i)) @@ -35,7 +35,7 @@ if tutorials: for i in range(1,tutorials+1): fn = '../../tutorial/tutorial{:02d}.yml'.format(i) print(fn) - wireviz.parse(fn, gen_bom=True) + wireviz.parse(fn, generate_bom=True) with open(os.path.abspath('../../tutorial/tutorial{:02d}.md'.format(i)), 'r') as info: for line in info: From 5d84bb86eb1e340ed964288a811ad2bd08794fac Mon Sep 17 00:00:00 2001 From: Daniel Rojas Date: Sun, 28 Jun 2020 11:43:31 +0200 Subject: [PATCH 11/12] Update gitignore --- src/wireviz/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/src/wireviz/.gitignore b/src/wireviz/.gitignore index 3000943..677cf18 100644 --- a/src/wireviz/.gitignore +++ b/src/wireviz/.gitignore @@ -1,2 +1,3 @@ __pycache__/ _test/ +wv-env/ From 7060c38f07c9eba575c4acc436eff191a6b9e192 Mon Sep 17 00:00:00 2001 From: Daniel Rojas Date: Sun, 28 Jun 2020 12:28:13 +0200 Subject: [PATCH 12/12] Add parse_file() function and use it in build_examples.py --- src/wireviz/build_examples.py | 6 +++--- src/wireviz/wireviz.py | 12 ++++++++++++ 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/src/wireviz/build_examples.py b/src/wireviz/build_examples.py index b7be539..fc04fce 100755 --- a/src/wireviz/build_examples.py +++ b/src/wireviz/build_examples.py @@ -15,7 +15,7 @@ if demos: for i in range(1,demos+1): fn = '../../examples/demo{:02d}.yml'.format(i) print(fn) - wireviz.parse(fn, generate_bom=True) + wireviz.parse_file(fn, generate_bom=True) if examples: with open(os.path.abspath('../../examples/readme.md'), 'w') as file: @@ -23,7 +23,7 @@ if examples: for i in range(1,examples+1): fn = '../../examples/ex{:02d}.yml'.format(i) print(fn) - wireviz.parse(fn, generate_bom=True) + wireviz.parse_file(fn, generate_bom=True) file.write('## Example {:02d}\n'.format(i)) file.write('![](ex{:02d}.png)\n\n'.format(i)) @@ -35,7 +35,7 @@ if tutorials: for i in range(1,tutorials+1): fn = '../../tutorial/tutorial{:02d}.yml'.format(i) print(fn) - wireviz.parse(fn, generate_bom=True) + wireviz.parse_file(fn, generate_bom=True) with open(os.path.abspath('../../tutorial/tutorial{:02d}.md'.format(i)), 'r') as info: for line in info: diff --git a/src/wireviz/wireviz.py b/src/wireviz/wireviz.py index fddbdd1..85a0361 100755 --- a/src/wireviz/wireviz.py +++ b/src/wireviz/wireviz.py @@ -618,6 +618,18 @@ def parse(yaml_input, file_out=None, generate_bom=False): h.output(filename=file_out, format=('png','svg'), gen_bom=generate_bom, view=False) +def parse_file(yaml_file, file_out=None, generate_bom=False): + with open(yaml_file, 'r') as file: + yaml_input = file.read() + + if not file_out: + fn, fext = os.path.splitext(yaml_file) + file_out = fn + file_out = os.path.abspath(file_out) + + parse(yaml_input, file_out=file_out, generate_bom=generate_bom) + + def parse_cmdline(): parser = argparse.ArgumentParser( description='Generate cable and wiring harness documentation from YAML descriptions'