--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/ProjectWeb/Html5ToCss3Converter.py Wed Dec 31 19:14:36 2014 +0100
@@ -0,0 +1,174 @@
+# -*- coding: utf-8 -*-
+
+# Copyright (c) 2014 Detlev Offenbach <detlev@die-offenbachs.de>
+#
+
+"""
+Module implementing the HTML5 to CSS3 converter.
+"""
+
+from __future__ import unicode_literals
+
+import os
+import datetime
+import getpass
+import random
+
+from PyQt5.QtCore import QObject
+from PyQt5.QtWidgets import QDialog
+
+from .Html5ToCss3ConverterParameterDialog import \
+ Html5ToCss3ConverterParameterDialog
+
+
+class Html5ToCss3Converter(QObject):
+ """
+ Class implementing the HTML5 to CSS3 converter.
+ """
+ CssTemplate7 = "{0}{1}{2}{3}{4}{5}{6}"
+ CssTemplate8 = "{0}{1}{2}{3}{4}{5}{6}{7}"
+ Placeholders = ('margin:0', 'padding:0', 'border:0', 'font-size:100%',
+ 'font:inherit', 'vertical-align:baseline', 'line-height:1',
+ 'outline:0', 'font-weight:inherit', 'font-style:inherit',
+ 'font-family:inherit', 'vertical-align:baseline')
+ CssToIgnore = ('head', 'meta', 'noscript', 'script', 'style', 'link',
+ 'no-js', 'title', 'object', 'col', 'colgroup', 'option',
+ 'param', 'audio', 'basefont', 'isindex', 'svg', 'area',
+ 'embed', 'br')
+
+ def __init__(self, html, parent=None):
+ """
+ Constructor
+
+ @param html HTML text to be converted (string)
+ @param parent reference to the parent object (QObject)
+ """
+ super(Html5ToCss3Converter, self).__init__(parent)
+
+ self.__html = html
+
+ def getCss3(self):
+ """
+ Public method to get the converted CSS3 text.
+
+ @return CSS3 text (string)
+ """
+ dlg = Html5ToCss3ConverterParameterDialog()
+ if dlg.exec_() == QDialog.Accepted:
+ indentation, placeholders = dlg.getData()
+
+ # TODO: implement this
+ self.__createSoup()
+
+ alreadyDone = list(self.CssToIgnore)
+
+ css = '@charset "utf-8";{0}'.format(os.linesep)
+ css += "/* {0} by {1}*/{2}".format(
+ datetime.datetime.now().isoformat().split(".")[0],
+ getpass.getuser(),
+ 2 * os.linesep
+ )
+
+ # step 1: tags
+ for tag in self.__getTags():
+ if tag not in alreadyDone:
+ css += self.CssTemplate7.format(
+ tag,
+ "{",
+ os.linesep,
+ indentation,
+ random.choice(self.Placeholders) + os.linesep
+ if placeholders else os.linesep,
+ "}",
+ os.linesep
+ )
+ alreadyDone.append(tag)
+ css += "/*{0}*/{1}".format(
+ "-" * 75,
+ os.linesep
+ )
+
+ # step 2: IDs
+ for id_ in self.__getIds():
+ if id_ not in alreadyDone:
+ css += "/* {0} */{1}".format(
+ "_".join(id_).lower(),
+ os.linesep
+ )
+ css += self.CssTemplate8.format(
+ "#",
+ id_[1],
+ "{",
+ os.linesep,
+ indentation,
+ random.choice(self.Placeholders) + os.linesep
+ if placeholders else os.linesep,
+ "}",
+ os.linesep
+ )
+ alreadyDone.append(id_)
+ css += "/*{0}*/{1}".format(
+ "-" * 75,
+ os.linesep
+ )
+
+ # step 3: classes
+ for class_ in self.__getClasses():
+ if class_ not in alreadyDone:
+ css += "/* {0} */{1}".format(
+ "_".join(class_).lower(),
+ os.linesep
+ )
+ css += self.CssTemplate8.format(
+ ".",
+ ", .".join(class_[1].split()),
+ "{",
+ os.linesep,
+ indentation,
+ random.choice(self.Placeholders) + os.linesep
+ if placeholders else os.linesep,
+ "}",
+ os.linesep
+ )
+ alreadyDone.append(class_)
+ else:
+ css = ""
+ return css.strip()
+
+ def __createSoup(self):
+ """
+ Private method to get a BeaitifulSoup object with our HTML text.
+ """
+ from bs4 import BeautifulSoup
+ self.__soup = BeautifulSoup(BeautifulSoup(self.__html).prettify())
+
+ def __getTags(self):
+ """
+ Private method to extract all tags of the HTML text.
+
+ @return list of all tags (list of strings)
+ """
+ tags = [t.name for t in self.__soup.find_all(True)]
+ return list(set(tags))
+
+ def __getClasses(self):
+ """
+ Private method to extract all classes of the HTML text.
+
+ @return list of tuples containing the tag name and its classes
+ as a blank separated string (list of tuples of two strings)
+ """
+ classes = [(t.name, " ".join(t["class"])) for t in
+ self.__soup.find_all(True, {"class": True})]
+ return sorted(list(set(classes)))
+
+ def __getIds(self):
+ """
+ Private method to extract all IDs of the HTML text.
+
+ @return list of tuples containing the tag name and its ID
+ (list of tuples of two strings)
+ """
+ ids = [(t.name, t["id"]) for t in
+ self.__soup.find_all(True, {"id": True})]
+ return sorted(list(set(ids)))
