Mercurial Repositories > Web Project and Tools / file comparison
comparison: ProjectWeb/Html5ToJsConverter.py
ProjectWeb/Html5ToJsConverter.py
- changeset 3
- e478a359e1fb
- child 4
- 6438afaad632
equal
deleted
inserted
replaced
| 2:917f93fc61dd | 3:e478a359e1fb |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 | |
| 3 # Copyright (c) 2014 Detlev Offenbach <detlev@die-offenbachs.de> | |
| 4 # | |
| 5 | |
| 6 """ | |
| 7 Module implementing the HTML5 to JavaScript converter. | |
| 8 """ | |
| 9 | |
| 10 from __future__ import unicode_literals | |
| 11 | |
| 12 import os | |
| 13 import re | |
| 14 import datetime | |
| 15 import getpass | |
| 16 | |
| 17 from PyQt5.QtCore import QObject | |
| 18 from PyQt5.QtWidgets import QDialog | |
| 19 | |
| 20 from .Html5ToJsConverterParameterDialog import \ | |
| 21 Html5ToJsConverterParameterDialog | |
| 22 | |
| 23 | |
| 24 class Html5ToJsConverter(QObject): | |
| 25 """ | |
| 26 Class implementing the HTML5 to JavaScript converter. | |
| 27 """ | |
| 28 JsTemplate8 = "{0}{1}{2}{3}{4}{5}{6}{7}" | |
| 29 TagsToIgnore = ('head', 'meta', 'noscript', 'script', 'style', 'link', | |
| 30 'no-js', 'title', 'object', 'col', 'colgroup', 'option', | |
| 31 'param', 'audio', 'basefont', 'isindex', 'svg', 'area', | |
| 32 'embed', 'br') | |
| 33 | |
| 34 def __init__(self, html, parent=None): | |
| 35 """ | |
| 36 Constructor | |
| 37 | |
| 38 @param html HTML text to be converted (string) | |
| 39 @param parent reference to the parent object (QObject) | |
| 40 """ | |
| 41 super(Html5ToJsConverter, self).__init__(parent) | |
| 42 | |
| 43 self.__html = html | |
| 44 | |
| 45 def getJavaScript(self): | |
| 46 """ | |
| 47 Public method to get the converted JavaScript text. | |
| 48 | |
| 49 @return JavaScript text (string) | |
| 50 """ | |
| 51 dlg = Html5ToJsConverterParameterDialog() | |
| 52 if dlg.exec_() == QDialog.Accepted: | |
| 53 indentation, scriptTags = dlg.getData() | |
| 54 | |
| 55 self.__createSoup() | |
| 56 | |
| 57 alreadyDone = list(self.TagsToIgnore) | |
| 58 | |
| 59 js = "<script>{0}".format(os.linesep) if scriptTags else "" | |
| 60 js += "// {0} by {1}{2}".format( | |
| 61 datetime.datetime.now().isoformat().split(".")[0], | |
| 62 getpass.getuser(), | |
| 63 os.linesep | |
| 64 ) | |
| 65 js += "$(document).ready(function(){" + os.linesep | |
| 66 | |
| 67 # step 1: IDs | |
| 68 js += "/*{0}*/{1}".format( | |
| 69 "-" * 75, | |
| 70 os.linesep | |
| 71 ) | |
| 72 for id_ in self.__getIds(): | |
| 73 if id_ not in alreadyDone: | |
| 74 js += "{0}// {1}{2}".format( | |
| 75 indentation, | |
| 76 "#".join(id_).lower(), | |
| 77 os.linesep | |
| 78 ) | |
| 79 js += self.JsTemplate8.format( | |
| 80 indentation, | |
| 81 "var ", | |
| 82 re.sub("[^a-z0-9]", "", | |
| 83 id_[1].lower() if len(id_[1]) < 11 else | |
| 84 re.sub("[aeiou]", "", id_[1].lower())), | |
| 85 " = ", | |
| 86 '$("#{0}").length'.format(id_[1]), | |
| 87 ";", | |
| 88 os.linesep, | |
| 89 os.linesep | |
| 90 ) | |
| 91 alreadyDone.append(id_) | |
| 92 | |
| 93 # step 2: classes | |
| 94 js += "/*{0}*/{1}".format( | |
| 95 "-" * 75, | |
| 96 os.linesep | |
| 97 ) | |
| 98 for class_ in self.__getClasses(): | |
| 99 if class_ not in alreadyDone: | |
| 100 js += "{0}// {1}{2}".format( | |
| 101 indentation, | |
| 102 ".".join(class_).lower(), | |
| 103 os.linesep | |
| 104 ) | |
| 105 js += self.JsTemplate8.format( | |
| 106 indentation, | |
| 107 "var ", | |
| 108 re.sub("[^a-z0-9]", "", | |
| 109 class_[1].lower() if len(class_[1]) < 11 else | |
| 110 re.sub("[aeiou]", "", class_[1].lower())), | |
| 111 " = ", | |
| 112 '$(".{0}").length'.format(class_[1]), | |
| 113 ";", | |
| 114 os.linesep, | |
| 115 os.linesep | |
| 116 ) | |
| 117 alreadyDone.append(class_) | |
| 118 | |
| 119 js += "})" | |
| 120 js += "{0}</script>".format(os.linesep) if scriptTags else "" | |
| 121 else: | |
| 122 js = "" | |
| 123 return js.strip() | |
| 124 | |
| 125 def __createSoup(self): | |
| 126 """ | |
| 127 Private method to get a BeaitifulSoup object with our HTML text. | |
| 128 """ | |
| 129 from bs4 import BeautifulSoup | |
| 130 self.__soup = BeautifulSoup(BeautifulSoup(self.__html).prettify()) | |
| 131 | |
| 132 def __getClasses(self): | |
| 133 """ | |
| 134 Private method to extract all classes of the HTML text. | |
| 135 | |
| 136 @return list of tuples containing the tag name and its classes | |
| 137 as a blank separated string (list of tuples of two strings) | |
| 138 """ | |
| 139 classes = [(t.name, " ".join(t["class"])) for t in | |
| 140 self.__soup.find_all(True, {"class": True})] | |
| 141 return sorted(list(set(classes))) | |
| 142 | |
| 143 def __getIds(self): | |
| 144 """ | |
| 145 Private method to extract all IDs of the HTML text. | |
| 146 | |
| 147 @return list of tuples containing the tag name and its ID | |
| 148 (list of tuples of two strings) | |
| 149 """ | |
| 150 ids = [(t.name, t["id"]) for t in | |
| 151 self.__soup.find_all(True, {"id": True})] | |
| 152 return sorted(list(set(ids))) |
