Source Code for Module nltk.misc.nemo

  1  #!/usr/bin/env python 
  2   
  3  # Finding (and Replacing) Nemo, Version 1.1, Aristide Grange 2006/06/06  
  4  # http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/496783 
  5   
  6  """ 
  7  Finding (and Replacing) Nemo 
  8   
  9  Instant Regular Expressions 
 10  Created by Aristide Grange 
 11  """ 
 12  import Tkinter as tk 
 13  import sre 
 14  import itertools 
 15   
 16  windowTitle = "Finding (and Replacing) Nemo" 
 17  initialFind = r"n(.*?)e(.*?)m(.*?)o" 
 18  initialRepl = r"M\1A\2K\3I" 
 19  initialText = """\ 
 20  Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. 
 21  Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. 
 22  Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. 
 23  Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. 
 24  """ 
 25  images = { 
 26      "FIND":"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", 
 27      "find":"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", 
 28      "REPL":"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", 
 29      "repl":"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", 
 30  } 
 31  colors = ["#FF7B39","#80F121"] 
 32  emphColors = ["#DAFC33","#F42548"] 
 33  fieldParams = { 
 34      "height":3, 
 35      "width":70, 
 36      "font":("monaco",14), 
 37      "highlightthickness":0, 
 38      "borderwidth":0, 
 39      "background":"white", 
 40  } 
 41  textParams = { 
 42      "bg":"#F7E0D4", 
 43      "fg":"#2321F1", 
 44      "highlightthickness":0, 
 45      "width":1, 
 46      "height":10, 
 47      "font":("verdana",16), 
 48      "wrap":"word", 
 49  } 
 50   
 51   
 52 -class Zone: 
 53 -    def __init__(self, image, initialField, initialText): 
 54          frm = tk.Frame(root) 
 55          frm.config(background="white") 
 56          self.image = tk.PhotoImage(format='gif',data=images[image.upper()]) 
 57          self.imageDimmed = tk.PhotoImage(format='gif',data=images[image]) 
 58          self.img = tk.Label(frm) 
 59          self.img.config(borderwidth=0) 
 60          self.img.pack(side = "left") 
 61          self.fld = tk.Text(frm, **fieldParams) 
 62          self.initScrollText(frm,self.fld,initialField) 
 63          frm = tk.Frame(root) 
 64          self.txt = tk.Text(frm, **textParams) 
 65          self.initScrollText(frm,self.txt,initialText) 
 66          for i in range(2): 
 67              self.txt.tag_config(colors[i], background = colors[i]) 
 68              self.txt.tag_config("emph"+colors[i], foreground = emphColors[i]) 
 69 -    def initScrollText(self,frm,txt,contents): 
 70          scl = tk.Scrollbar(frm) 
 71          scl.config(command = txt.yview) 
 72          scl.pack(side="right",fill="y") 
 73          txt.pack(side = "left", expand=True, fill="x") 
 74          txt.config(yscrollcommand = scl.set) 
 75          txt.insert("1.0",contents) 
 76          frm.pack(fill = "x") 
 77          tk.Frame(height=2, bd=1, relief="ridge").pack(fill="x") 
 78 -    def refresh(self): 
 79          self.colorCycle = itertools.cycle(colors) 
 80          try: 
 81              self.substitute() 
 82              self.img.config(image = self.image) 
 83          except sre.error: 
 84              self.img.config(image = self.imageDimmed) 
 85   
 86   
 87 -class FindZone(Zone): 
 88 -    def addTags(self,m): 
 89          color = self.colorCycle.next() 
 90          self.txt.tag_add(color,"1.0+%sc"%m.start(),"1.0+%sc"%m.end()) 
 91          try: 
 92              self.txt.tag_add("emph"+color,"1.0+%sc"%m.start("emph"), 
 93                               "1.0+%sc"%m.end("emph")) 
 94          except: 
 95              pass 
 96 -    def substitute(self,*args): 
 97          for color in colors: 
 98              self.txt.tag_remove(color,"1.0","end") 
 99              self.txt.tag_remove("emph"+color,"1.0","end") 
100          self.rex = sre.compile("") # default value in case of misformed regexp 
101          self.rex = sre.compile(self.fld.get("1.0","end")[:-1],sre.MULTILINE) 
102          try: 
103              sre.compile("(?P<emph>%s)" % self.fld.get(tk.SEL_FIRST, 
104                                                        tk.SEL_LAST)) 
105              self.rexSel = sre.compile("%s(?P<emph>%s)%s" % ( 
106                  self.fld.get("1.0",tk.SEL_FIRST), 
107                  self.fld.get(tk.SEL_FIRST,tk.SEL_LAST), 
108                  self.fld.get(tk.SEL_LAST,"end")[:-1], 
109              ),sre.MULTILINE) 
110          except: 
111              self.rexSel = self.rex 
112          self.rexSel.sub(self.addTags,self.txt.get("1.0","end")) 
113   
114   
115 -class ReplaceZone(Zone): 
116 -    def addTags(self,m): 
117          s = sz.rex.sub(self.repl,m.group()) 
118          self.txt.delete("1.0+%sc"%(m.start()+self.diff), 
119                          "1.0+%sc"%(m.end()+self.diff)) 
120          self.txt.insert("1.0+%sc"%(m.start()+self.diff),s, 
121                          self.colorCycle.next()) 
122          self.diff += len(s) - (m.end() - m.start()) 
123 -    def substitute(self): 
124          self.txt.delete("1.0","end") 
125          self.txt.insert("1.0",sz.txt.get("1.0","end")[:-1]) 
126          self.diff = 0 
127          self.repl = rex0.sub(r"\\g<\1>",self.fld.get("1.0","end")[:-1]) 
128          sz.rex.sub(self.addTags,sz.txt.get("1.0","end")[:-1]) 
129   
130   
131 -def launchRefresh(_): 
132      sz.fld.after_idle(sz.refresh) 
133      rz.fld.after_idle(rz.refresh) 
134   
135   
136  if __name__ == '__main__': 
137      root = tk.Tk() 
138      root.resizable(height=False,width=True) 
139      root.title(windowTitle) 
140      root.minsize(width=250,height=0) 
141      sz = FindZone("find",initialFind,initialText) 
142      sz.fld.bind("<Button-1>",launchRefresh) 
143      sz.fld.bind("<ButtonRelease-1>",launchRefresh) 
144      sz.fld.bind("<B1-Motion>",launchRefresh) 
145      sz.rexSel = sre.compile("") 
146      rz = ReplaceZone("repl",initialRepl,"") 
147      rex0 = sre.compile(r"(?<!\\)\\([0-9]+)") 
148      root.bind_all("<Key>",launchRefresh) 
149      launchRefresh(None) 
150      root.mainloop() 
151