1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
|
import re, STDOM
from string import split, join, replace, expandtabs, strip, find
#####################################################################
# Updated functions #
#####################################################################
def indention(str,front = re.compile("^\s+").match):
"""
Find the number of leading spaces. If none, return 0.
"""
result = front(str)
if result is not None:
start, end = result.span()
return end-start
else:
return 0 # no leading spaces
def insert(struct, top, level):
"""
find what will be the parant paragraph of
a sentence and return that paragraph's
sub-paragraphs. The new paragraph will be
appended to those sub-paragraphs
"""
#print "struct", struct, top-1
if not top-1 in range(len(struct)):
if struct:
return struct[len(struct)-1].getSubparagraphs()
return struct
run = struct[top-1]
i = 0
while i+1 < level:
run = run.getSubparagraphs()[len(run.getSubparagraphs())-1]
i = i + 1
#print "parent for level ", level, " was => ", run.getColorizableTexts()
return run.getSubparagraphs()
def display(struct):
"""
runs through the structure and prints out
the paragraphs. If the insertion works
correctly, display's results should mimic
the orignal paragraphs.
"""
if struct.getColorizableTexts():
print join(struct.getColorizableTexts()),"\n"
if struct.getSubparagraphs():
for x in struct.getSubparagraphs():
display(x)
def display2(struct):
"""
runs through the structure and prints out
the paragraphs. If the insertion works
correctly, display's results should mimic
the orignal paragraphs.
"""
if struct.getNodeValue():
print struct.getNodeValue(),"\n"
if struct.getSubparagraphs():
for x in struct.getSubparagraphs():
display(x)
def findlevel(levels,indent):
"""
remove all level information of levels
with a greater level of indentation.
Then return which level should insert this
paragraph
"""
keys = levels.keys()
for key in keys:
if levels[key] > indent:
del(levels[key])
keys = levels.keys()
if not(keys):
return 0
else:
for key in keys:
if levels[key] == indent:
return key
highest = 0
for key in keys:
if key > highest:
highest = key
return highest-1
para_delim = r'(\n\s*\n|\r\n\s*\r\n)' # UNIX or DOS line endings, respectively
#####################################################################
# Golly, the capitalization of this function always makes me think it's a class
def StructuredText(paragraphs, delimiter=re.compile(para_delim)):
"""
StructuredText accepts paragraphs, which is a list of
lines to be parsed. StructuredText creates a structure
which mimics the structure of the paragraphs.
Structure => [paragraph,[sub-paragraphs]]
"""
currentlevel = 0
currentindent = 0
levels = {0:0}
level = 0 # which header are we under
struct = [] # the structure to be returned
run = struct
paragraphs = expandtabs(paragraphs)
paragraphs = '%s%s%s' % ('\n\n', paragraphs, '\n\n')
paragraphs = delimiter.split(paragraphs)
paragraphs = filter(strip, paragraphs)
if not paragraphs: return StructuredTextDocument()
ind = [] # structure based on indention levels
for paragraph in paragraphs:
ind.append([indention(paragraph), paragraph])
currentindent = indention(paragraphs[0])
levels[0] = currentindent
#############################################################
# updated #
#############################################################
for indent,paragraph in ind :
if indent == 0:
level = level + 1
currentlevel = 0
currentindent = 0
levels = {0:0}
struct.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
elif indent > currentindent:
currentlevel = currentlevel + 1
currentindent = indent
levels[currentlevel] = indent
run = insert(struct,level,currentlevel)
run.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
elif indent < currentindent:
result = findlevel(levels,indent)
if result > 0:
currentlevel = result
currentindent = indent
if not level:
struct.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
else:
run = insert(struct,level,currentlevel)
run.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
else:
if insert(struct,level,currentlevel):
run = insert(struct,level,currentlevel)
else:
run = struct
currentindet = indent
run.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
return StructuredTextDocument(struct)
Basic = StructuredText
class StructuredTextParagraph(STDOM.Element):
indent=0
def __init__(self, src, subs=None, **kw):
if subs is None: subs=[]
self._src=src
self._subs=list(subs)
self._attributes=kw.keys()
for k, v in kw.items(): setattr(self, k, v)
def getChildren(self, type=type, lt=type([])):
src=self._src
if type(src) is not lt: src=[src]
return src+self._subs
def getAttribute(self, name):
return getattr(self, name, None)
def getAttributeNode(self, name):
if hasattr(self, name):
return STDOM.Attr(name, getattr(self, name))
def getAttributes(self):
d={}
for a in self._attributes:
d[a]=getattr(self, a, '')
return STDOM.NamedNodeMap(d)
def getSubparagraphs(self):
return self._subs
def setSubparagraphs(self, subs):
self._subs=subs
def getColorizableTexts(self):
return (self._src,)
def setColorizableTexts(self, src):
self._src=src[0]
def __repr__(self):
r=[]; a=r.append
a((' '*(self.indent or 0))+
('%s(' % self.__class__.__name__)
+str(self._src)+', ['
)
for p in self._subs: a(`p`)
a((' '*(self.indent or 0))+'])')
return join(r,'\n')
"""
create aliases for all above functions in the pythony way.
"""
def _get_Children(self, type=type, lt=type([])):
return self.getChildren(type,lt)
def _get_Attribute(self, name):
return self.getAttribute(name)
def _get_AttributeNode(self, name):
return self.getAttributeNode(name)
def _get_Attributes(self):
return self.getAttributes()
def _get_Subparagraphs(self):
return self.getSubparagraphs()
def _set_Subparagraphs(self, subs):
return self.setSubparagraphs(subs)
def _get_ColorizableTexts(self):
return self.getColorizableTexts()
def _set_ColorizableTexts(self, src):
return self.setColorizableTexts(src)
class StructuredTextDocument(StructuredTextParagraph):
"""
A StructuredTextDocument holds StructuredTextParagraphs
as its subparagraphs.
"""
_attributes=()
def __init__(self, subs=None, **kw):
apply(StructuredTextParagraph.__init__,
(self, '', subs),
kw)
def getChildren(self):
return self._subs
def getColorizableTexts(self):
return ()
def setColorizableTexts(self, src):
pass
def __repr__(self):
r=[]; a=r.append
a('%s([' % self.__class__.__name__)
for p in self._subs: a(`p`+',')
a('])')
return join(r,'\n')
"""
create aliases for all above functions in the pythony way.
"""
def _get_Children(self):
return self.getChildren()
def _get_ColorizableTexts(self):
return self.getColorizableTexts()
def _set_ColorizableTexts(self, src):
return self.setColorizableTexts(src)
|
