Since I have connectivity problems now and then, I wrote a mini-app using PyQt to give me the basic features of Ishida's UniView (which also seems to have had some server problems recently)... Maybe it would be useful to others also so I'm posting here. It's under the GPL since I use PyQt under the GPL.
Since it depends on PyQt, it is probably immediately usable by Linux users, esp. who use distros which have PyQt pre-installed or installable by a single command like apt-get or yum. On other platforms, you'll have to have installed Python and PyQt as appropriate... BTW I use Py3, so maybe a few tweaks would be needed to get it working with Py2. Since it's GPL, please feel free to make derivatives. I hope the name "UniView" is not copyrighted or anything. Certainly don't intend to infringe... -- Shriramana Sharma ஶ்ரீரமணஶர்மா श्रीरमणशर्मा
#! /usr/bin/env python3 # UniView -- to list the list of Unicode characters in an input string # (C) Shriramana Sharma, 2014 # Licence: GPLv3 from PyQt4.QtCore import * from PyQt4.QtGui import * import re import unicodedata def code ( char, smpLen = 6 ) : c = hex(ord(char))[2:] if len(c) < 4 : c = c.zfill(4) elif len(c) < smpLen : c = c.zfill(smpLen) return c def joinSurrogates(match) : SURROGATE_OFFSET = 0x10000 - ( 0xD800 << 10 ) - 0xDC00 return chr ( ( ord(match.group(1)) << 10 ) + ord(match.group(2)) + SURROGATE_OFFSET ) def fixSurrogatePresence(s) : '''Returns the input UTF-16 string with surrogate pairs replaced by the character they represent''' # ideas from: # http://www.unicode.org/faq/utf_bom.html#utf16-4 # http://stackoverflow.com/a/6928284/1503120 return re.sub ( '([\uD800-\uDBFF])([\uDC00-\uDFFF])', joinSurrogates, s ) def setComboItem(cb,s) : for i in range(cb.count()) : if cb.itemText(i) == s : cb.setCurrentIndex(i) class MainWindow(QWidget) : def __init__(self) : QWidget.__init__(self) self.setObjectName("mainWindow") self.setWindowTitle("UniView") self.inputTextBox = QPlainTextEdit() w = self.inputLabel = QLabel("&Input text") w.setBuddy(self.inputTextBox) self.analyseButton = QPushButton("&Analyse") w = self.tabWidget = QTabWidget() self.tableTab = QTableView() self.stringTab = QWidget() w.addTab ( self.tableTab, "As a &table" ) w.addTab ( self.stringTab, "As a st&ring" ) # contents of string tab w = self.outputTextBox = QPlainTextEdit() w.setReadOnly(True) w = self.outputLabel = QLabel("&Codepoints") w.setBuddy(self.outputTextBox) w = self.presetComboBox = QComboBox() w.addItem("Simple") w.addItem("Python") w.addItem("Custom") w = self.presetLabel = QLabel("<b>&Presets</b>") w.setBuddy(self.presetComboBox) w = self.hexCaseComboBox = QComboBox() w.addItem("ABCDEF") w.addItem("abcdef") w = self.hexCaseLabel = QLabel("&Hex digits case") w.setBuddy(self.hexCaseComboBox) w = self.bmpPrefixComboBox = QComboBox() w.addItem("U+") w.addItem("\\u") w.setEditable(True) w = self.bmpPrefixLabel = QLabel("&BMP Prefix") w.setBuddy(self.bmpPrefixComboBox) w = self.smpPrefixComboBox = QComboBox() w.addItem("U+") w.addItem("\\U") w.setEditable(True) w = self.smpPrefixLabel = QLabel("&SMP Prefix") w.setBuddy(self.smpPrefixComboBox) w = self.smpCodeLengthComboBox = QComboBox() w.addItem("6") w.addItem("8") w = self.smpCodeLengthLabel = QLabel("SMP Hex &Length") w.setBuddy(self.smpCodeLengthComboBox) w = self.delimeterComboBox = QComboBox() w.addItem("(space)") w.addItem("(none)") w.addItem(",") w.setEditable(True) w = self.delimeterLabel = QLabel("&Delimeter") w.setBuddy(self.delimeterComboBox) l = self.presetGrid = QGridLayout() l.addWidget ( self.presetLabel, 0, 0 ) l.addWidget ( self.presetComboBox, 0, 1 ) l.addWidget ( self.hexCaseLabel, 0, 3 ) l.addWidget ( self.hexCaseComboBox, 0, 4 ) l.addWidget ( self.bmpPrefixLabel, 1, 0 ) l.addWidget ( self.bmpPrefixComboBox, 1, 1 ) l.addWidget ( self.delimeterLabel, 1, 3 ) l.addWidget ( self.delimeterComboBox, 1, 4 ) l.addWidget ( self.smpPrefixLabel, 2, 0 ) l.addWidget ( self.smpPrefixComboBox, 2, 1 ) l.addWidget ( self.smpCodeLengthLabel, 2, 3 ) l.addWidget ( self.smpCodeLengthComboBox, 2, 4 ) l.setColumnMinimumWidth ( 2, 20 ) w = self.presetGroupBox = QGroupBox("String output config") w.setLayout(l) l = self.stringTabLayout = QVBoxLayout() l.addWidget(self.outputLabel) l.addWidget(self.outputTextBox) l.addWidget(self.presetGroupBox) self.stringTab.setLayout(l) l = self.mainLayout = QVBoxLayout() l.addWidget(self.inputLabel) l.addWidget(self.inputTextBox) l.addWidget(self.analyseButton) l.addWidget(self.tabWidget) self.setLayout(l) QObject.connect ( self.analyseButton, SIGNAL("clicked()"), self.analyseText ) QObject.connect ( self.presetComboBox, SIGNAL("currentIndexChanged(const QString &)"), self.presetChanged ) for cbn in "bmpPrefix", "smpPrefix", "smpCodeLength", "delimeter" : QObject.connect ( self.__dict__ [ cbn + "ComboBox" ], SIGNAL("currentIndexChanged(const QString &)"), lambda: setComboItem ( self.presetComboBox, "Custom" ) ) def analyseText(self) : bmpPrefix = self.bmpPrefixComboBox.currentText() smpPrefix = self.smpPrefixComboBox.currentText() smpCodeLength = int(self.smpCodeLengthComboBox.currentText()) capitalHex = self.hexCaseComboBox.currentText() == "ABCDEF" delimeter = self.delimeterComboBox.currentText() if delimeter == "(none)" : delimeter = "" elif delimeter == "(space)" : delimeter = " " text = fixSurrogatePresence(self.inputTextBox.toPlainText()) out = "" for char in text : if out != "" : out += delimeter out += smpPrefix if ord(char) > 0xffff else bmpPrefix c = code(char,smpCodeLength) out += c.upper() if capitalHex else c self.outputTextBox.setPlainText(out) tableModel = QStandardItemModel ( len(text), 2 ) tableModel.setHeaderData ( 0, Qt.Horizontal, "Codepoint" ) tableModel.setHeaderData ( 1, Qt.Horizontal, "Character name" ) for i in range(len(text)) : tableModel.setItem ( i, 0, QStandardItem ( "U+" + code(text[i]).upper() ) ) tableModel.setItem ( i, 1, QStandardItem ( unicodedata.name ( text[i], "UNKNOWN" ) ) ) self.tableTab.setModel(tableModel) self.tableTab.horizontalHeader().setStretchLastSection(True) presetMap = { "Simple": { "bmpPrefix": "U+", "smpPrefix": "U+", "delimeter": "(space)", "smpCodeLength": "6" }, "Python": { "bmpPrefix": "\\u", "smpPrefix": "\\U", "delimeter": "(none)", "smpCodeLength": "8" } } def presetChanged ( self, newPresetName ) : if newPresetName == "Custom" : return for k,v in MainWindow.presetMap[newPresetName].items() : setComboItem ( self.__dict__ [ k + "ComboBox" ], v ) setComboItem ( self.presetComboBox, newPresetName ) # needed since above actions may reset this to Custom app = QApplication([]) mainWindow = MainWindow() mainWindow.show() app.exec_() # राम ராம രാമ ರಾಮ రామ rāma 𑀭𑀸𑀫
_______________________________________________ Unicode mailing list Unicode@unicode.org http://unicode.org/mailman/listinfo/unicode
