marcus/scour
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

initial source import (v0.26) and packaging

Browse source
This commit is contained in:
Tobias Oberstein 2013-10-22 16:31:42 +02:00
parent f3a7507d82
commit f89b6bbf6a
11 changed files with 4134 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

22
scour/__init__.py Normal file
View file

@ -0,0 +1,22 @@
###############################################################################
##
## Copyright (C) 2013 Tavendo GmbH
##
## Licensed under the Apache License, Version 2.0 (the "License");
## you may not use this file except in compliance with the License.
## You may obtain a copy of the License at
##
## http://www.apache.org/licenses/LICENSE-2.0
##
## Unless required by applicable law or agreed to in writing, software
## distributed under the License is distributed on an "AS IS" BASIS,
## WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
## See the License for the specific language governing permissions and
## limitations under the License.
##
###############################################################################
import scour
import svg_regex
import svg_transform
import yocto_css

3206
scour/scour.py Normal file
View file

File diff suppressed because it is too large Load diff

285
scour/svg_regex.py Normal file
View file

@ -0,0 +1,285 @@
# This software is OSI Certified Open Source Software.
# OSI Certified is a certification mark of the Open Source Initiative.
#
# Copyright (c) 2006, Enthought, Inc.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
# * Neither the name of Enthought, Inc. nor the names of its contributors may
# be used to endorse or promote products derived from this software without
# specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
# ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
# ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
""" Small hand-written recursive descent parser for SVG <path> data.
In [1]: from svg_regex import svg_parser
In [3]: svg_parser.parse('M 10,20 30,40V50 60 70')
Out[3]: [('M', [(10.0, 20.0), (30.0, 40.0)]), ('V', [50.0, 60.0, 70.0])]
In [4]: svg_parser.parse('M 0.6051.5') # An edge case
Out[4]: [('M', [(0.60509999999999997, 0.5)])]
In [5]: svg_parser.parse('M 100-200') # Another edge case
Out[5]: [('M', [(100.0, -200.0)])]
"""
import re
from decimal import *
# Sentinel.
class _EOF(object):
def __repr__(self):
return 'EOF'
EOF = _EOF()
lexicon = [
('float', r'[-+]?(?:(?:[0-9]*\.[0-9]+)|(?:[0-9]+\.?))(?:[Ee][-+]?[0-9]+)?'),
('int', r'[-+]?[0-9]+'),
('command', r'[AaCcHhLlMmQqSsTtVvZz]'),
]
class Lexer(object):
""" Break SVG path data into tokens.
The SVG spec requires that tokens are greedy. This lexer relies on Python's
regexes defaulting to greediness.
This style of implementation was inspired by this article:
http://www.gooli.org/blog/a-simple-lexer-in-python/
"""
def __init__(self, lexicon):
self.lexicon = lexicon
parts = []
for name, regex in lexicon:
parts.append('(?P<%s>%s)' % (name, regex))
self.regex_string = '|'.join(parts)
self.regex = re.compile(self.regex_string)
def lex(self, text):
""" Yield (token_type, str_data) tokens.
The last token will be (EOF, None) where EOF is the singleton object
defined in this module.
"""
for match in self.regex.finditer(text):
for name, _ in self.lexicon:
m = match.group(name)
if m is not None:
yield (name, m)
break
yield (EOF, None)
svg_lexer = Lexer(lexicon)
class SVGPathParser(object):
""" Parse SVG <path> data into a list of commands.
Each distinct command will take the form of a tuple (command, data). The
`command` is just the character string that starts the command group in the
<path> data, so 'M' for absolute moveto, 'm' for relative moveto, 'Z' for
closepath, etc. The kind of data it carries with it depends on the command.
For 'Z' (closepath), it's just None. The others are lists of individual
argument groups. Multiple elements in these lists usually mean to repeat the
command. The notable exception is 'M' (moveto) where only the first element
is truly a moveto. The remainder are implicit linetos.
See the SVG documentation for the interpretation of the individual elements
for each command.
The main method is `parse(text)`. It can only consume actual strings, not
filelike objects or iterators.
"""
def __init__(self, lexer=svg_lexer):
self.lexer = lexer
self.command_dispatch = {
'Z': self.rule_closepath,
'z': self.rule_closepath,
'M': self.rule_moveto_or_lineto,
'm': self.rule_moveto_or_lineto,
'L': self.rule_moveto_or_lineto,
'l': self.rule_moveto_or_lineto,
'H': self.rule_orthogonal_lineto,
'h': self.rule_orthogonal_lineto,
'V': self.rule_orthogonal_lineto,
'v': self.rule_orthogonal_lineto,
'C': self.rule_curveto3,
'c': self.rule_curveto3,
'S': self.rule_curveto2,
's': self.rule_curveto2,
'Q': self.rule_curveto2,
'q': self.rule_curveto2,
'T': self.rule_curveto1,
't': self.rule_curveto1,
'A': self.rule_elliptical_arc,
'a': self.rule_elliptical_arc,
}
# self.number_tokens = set(['int', 'float'])
self.number_tokens = list(['int', 'float'])
def parse(self, text):
""" Parse a string of SVG <path> data.
"""
next = self.lexer.lex(text).next
token = next()
return self.rule_svg_path(next, token)
def rule_svg_path(self, next, token):
commands = []
while token[0] is not EOF:
if token[0] != 'command':
raise SyntaxError("expecting a command; got %r" % (token,))
rule = self.command_dispatch[token[1]]
command_group, token = rule(next, token)
commands.append(command_group)
return commands
def rule_closepath(self, next, token):
command = token[1]
token = next()
return (command, []), token
def rule_moveto_or_lineto(self, next, token):
command = token[1]
token = next()
coordinates = []
while token[0] in self.number_tokens:
pair, token = self.rule_coordinate_pair(next, token)
coordinates.extend(pair)
return (command, coordinates), token
def rule_orthogonal_lineto(self, next, token):
command = token[1]
token = next()
coordinates = []
while token[0] in self.number_tokens:
coord, token = self.rule_coordinate(next, token)
coordinates.append(coord)
return (command, coordinates), token
def rule_curveto3(self, next, token):
command = token[1]
token = next()
coordinates = []
while token[0] in self.number_tokens:
pair1, token = self.rule_coordinate_pair(next, token)
pair2, token = self.rule_coordinate_pair(next, token)
pair3, token = self.rule_coordinate_pair(next, token)
coordinates.extend(pair1)
coordinates.extend(pair2)
coordinates.extend(pair3)
return (command, coordinates), token
def rule_curveto2(self, next, token):
command = token[1]
token = next()
coordinates = []
while token[0] in self.number_tokens:
pair1, token = self.rule_coordinate_pair(next, token)
pair2, token = self.rule_coordinate_pair(next, token)
coordinates.extend(pair1)
coordinates.extend(pair2)
return (command, coordinates), token
def rule_curveto1(self, next, token):
command = token[1]
token = next()
coordinates = []
while token[0] in self.number_tokens:
pair1, token = self.rule_coordinate_pair(next, token)
coordinates.extend(pair1)
return (command, coordinates), token
def rule_elliptical_arc(self, next, token):
command = token[1]
token = next()
arguments = []
while token[0] in self.number_tokens:
rx = Decimal(token[1]) * 1
if rx < Decimal("0.0"):
raise SyntaxError("expecting a nonnegative number; got %r" % (token,))
token = next()
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
ry = Decimal(token[1]) * 1
if ry < Decimal("0.0"):
raise SyntaxError("expecting a nonnegative number; got %r" % (token,))
token = next()
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
axis_rotation = Decimal(token[1]) * 1
token = next()
if token[1] not in ('0', '1'):
raise SyntaxError("expecting a boolean flag; got %r" % (token,))
large_arc_flag = Decimal(token[1]) * 1
token = next()
if token[1] not in ('0', '1'):
raise SyntaxError("expecting a boolean flag; got %r" % (token,))
sweep_flag = Decimal(token[1]) * 1
token = next()
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
x = Decimal(token[1]) * 1
token = next()
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
y = Decimal(token[1]) * 1
token = next()
arguments.extend([rx, ry, axis_rotation, large_arc_flag, sweep_flag, x, y])
return (command, arguments), token
def rule_coordinate(self, next, token):
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
x = getcontext().create_decimal(token[1])
token = next()
return x, token
def rule_coordinate_pair(self, next, token):
# Inline these since this rule is so common.
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
x = getcontext().create_decimal(token[1])
token = next()
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
y = getcontext().create_decimal(token[1])
token = next()
return [x, y], token
svg_parser = SVGPathParser()

233
scour/svg_transform.py Normal file
View file

@ -0,0 +1,233 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# SVG transformation list parser
#
# Copyright 2010 Louis Simard
#
# This file is part of Scour, http://www.codedread.com/scour/
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" Small recursive descent parser for SVG transform="" data.
In [1]: from svg_transform import svg_transform_parser
In [3]: svg_transform_parser.parse('translate(50, 50)')
Out[3]: [('translate', [50.0, 50.0])]
In [4]: svg_transform_parser.parse('translate(50)')
Out[4]: [('translate', [50.0])]
In [5]: svg_transform_parser.parse('rotate(36 50,50)')
Out[5]: [('rotate', [36.0, 50.0, 50.0])]
In [6]: svg_transform_parser.parse('rotate(36)')
Out[6]: [('rotate', [36.0])]
In [7]: svg_transform_parser.parse('skewX(20)')
Out[7]: [('skewX', [20.0])]
In [8]: svg_transform_parser.parse('skewY(40)')
Out[8]: [('skewX', [20.0])]
In [9]: svg_transform_parser.parse('scale(2 .5)')
Out[9]: [('scale', [2.0, 0.5])]
In [10]: svg_transform_parser.parse('scale(.5)')
Out[10]: [('scale', [0.5])]
In [11]: svg_transform_parser.parse('matrix(1 0 50 0 1 80)')
Out[11]: [('matrix', [1.0, 0.0, 50.0, 0.0, 1.0, 80.0])]
Multiple transformations are supported:
In [12]: svg_transform_parser.parse('translate(30 -30) rotate(36)')
Out[12]: [('translate', [30.0, -30.0]), ('rotate', [36.0])]
"""
import re
from decimal import *
# Sentinel.
class _EOF(object):
def __repr__(self):
return 'EOF'
EOF = _EOF()
lexicon = [
('float', r'[-+]?(?:(?:[0-9]*\.[0-9]+)|(?:[0-9]+\.?))(?:[Ee][-+]?[0-9]+)?'),
('int', r'[-+]?[0-9]+'),
('command', r'(?:matrix|translate|scale|rotate|skew[XY])'),
('coordstart', r'\('),
('coordend', r'\)'),
]
class Lexer(object):
""" Break SVG path data into tokens.
The SVG spec requires that tokens are greedy. This lexer relies on Python's
regexes defaulting to greediness.
This style of implementation was inspired by this article:
http://www.gooli.org/blog/a-simple-lexer-in-python/
"""
def __init__(self, lexicon):
self.lexicon = lexicon
parts = []
for name, regex in lexicon:
parts.append('(?P<%s>%s)' % (name, regex))
self.regex_string = '|'.join(parts)
self.regex = re.compile(self.regex_string)
def lex(self, text):
""" Yield (token_type, str_data) tokens.
The last token will be (EOF, None) where EOF is the singleton object
defined in this module.
"""
for match in self.regex.finditer(text):
for name, _ in self.lexicon:
m = match.group(name)
if m is not None:
yield (name, m)
break
yield (EOF, None)
svg_lexer = Lexer(lexicon)
class SVGTransformationParser(object):
""" Parse SVG transform="" data into a list of commands.
Each distinct command will take the form of a tuple (type, data). The
`type` is the character string that defines the type of transformation in the
transform data, so either of "translate", "rotate", "scale", "matrix",
"skewX" and "skewY". Data is always a list of numbers contained within the
transformation's parentheses.
See the SVG documentation for the interpretation of the individual elements
for each transformation.
The main method is `parse(text)`. It can only consume actual strings, not
filelike objects or iterators.
"""
def __init__(self, lexer=svg_lexer):
self.lexer = lexer
self.command_dispatch = {
'translate': self.rule_1or2numbers,
'scale': self.rule_1or2numbers,
'skewX': self.rule_1number,
'skewY': self.rule_1number,
'rotate': self.rule_1or3numbers,
'matrix': self.rule_6numbers,
}
# self.number_tokens = set(['int', 'float'])
self.number_tokens = list(['int', 'float'])
def parse(self, text):
""" Parse a string of SVG transform="" data.
"""
next = self.lexer.lex(text).next
commands = []
token = next()
while token[0] is not EOF:
command, token = self.rule_svg_transform(next, token)
commands.append(command)
return commands
def rule_svg_transform(self, next, token):
if token[0] != 'command':
raise SyntaxError("expecting a transformation type; got %r" % (token,))
command = token[1]
rule = self.command_dispatch[command]
token = next()
if token[0] != 'coordstart':
raise SyntaxError("expecting '('; got %r" % (token,))
numbers, token = rule(next, token)
if token[0] != 'coordend':
raise SyntaxError("expecting ')'; got %r" % (token,))
token = next()
return (command, numbers), token
def rule_1or2numbers(self, next, token):
numbers = []
# 1st number is mandatory
token = next()
number, token = self.rule_number(next, token)
numbers.append(number)
# 2nd number is optional
number, token = self.rule_optional_number(next, token)
if number is not None:
numbers.append(number)
return numbers, token
def rule_1number(self, next, token):
# this number is mandatory
token = next()
number, token = self.rule_number(next, token)
numbers = [number]
return numbers, token
def rule_1or3numbers(self, next, token):
numbers = []
# 1st number is mandatory
token = next()
number, token = self.rule_number(next, token)
numbers.append(number)
# 2nd number is optional
number, token = self.rule_optional_number(next, token)
if number is not None:
# but, if the 2nd number is provided, the 3rd is mandatory.
# we can't have just 2.
numbers.append(number)
number, token = self.rule_number(next, token)
numbers.append(number)
return numbers, token
def rule_6numbers(self, next, token):
numbers = []
token = next()
# all numbers are mandatory
for i in xrange(6):
number, token = self.rule_number(next, token)
numbers.append(number)
return numbers, token
def rule_number(self, next, token):
if token[0] not in self.number_tokens:
raise SyntaxError("expecting a number; got %r" % (token,))
x = Decimal(token[1]) * 1
token = next()
return x, token
def rule_optional_number(self, next, token):
if token[0] not in self.number_tokens:
return None, token
else:
x = Decimal(token[1]) * 1
token = next()
return x, token
svg_transform_parser = SVGTransformationParser()

72
scour/yocto_css.py Normal file
View file

@ -0,0 +1,72 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# yocto-css, an extremely bare minimum CSS parser
#
# Copyright 2009 Jeff Schiller
#
# This file is part of Scour, http://www.codedread.com/scour/
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# In order to resolve Bug 368716 (https://bugs.launchpad.net/scour/+bug/368716)
# scour needed a bare-minimum CSS parser in order to determine if some elements
# were still referenced by CSS properties.
# I looked at css-py (a CSS parser built in Python), but that library
# is about 35k of Python and requires ply to be installed. I just need
# something very basic to suit scour's needs.
# yocto-css takes a string of CSS and tries to spit out a list of rules
# A rule is an associative array (dictionary) with the following keys:
# - selector: contains the string of the selector (see CSS grammar)
# - properties: contains an associative array of CSS properties for this rule
# TODO: need to build up some unit tests for yocto_css
# stylesheet : [ CDO | CDC | S | statement ]*;
# statement : ruleset | at-rule;
# at-rule : ATKEYWORD S* any* [ block | ';' S* ];
# block : '{' S* [ any | block | ATKEYWORD S* | ';' S* ]* '}' S*;
# ruleset : selector? '{' S* declaration? [ ';' S* declaration? ]* '}' S*;
# selector : any+;
# declaration : property S* ':' S* value;
# property : IDENT;
# value : [ any | block | ATKEYWORD S* ]+;
# any : [ IDENT | NUMBER | PERCENTAGE | DIMENSION | STRING
# | DELIM | URI | HASH | UNICODE-RANGE | INCLUDES
# | DASHMATCH | FUNCTION S* any* ')'
# | '(' S* any* ')' | '[' S* any* ']' ] S*;
def parseCssString(str):
rules = []
# first, split on } to get the rule chunks
chunks = str.split('}')
for chunk in chunks:
# second, split on { to get the selector and the list of properties
bits = chunk.split('{')
if len(bits) != 2: continue
rule = {}
rule['selector'] = bits[0].strip()
# third, split on ; to get the property declarations
bites = bits[1].strip().split(';')
if len(bites) < 1: continue
props = {}
for bite in bites:
# fourth, split on : to get the property name and value
nibbles = bite.strip().split(':')
if len(nibbles) != 2: continue
props[nibbles[0].strip()] = nibbles[1].strip()
rule['properties'] = props
rules.append(rule)
return rules