code_zauker 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/BUGS.org +4 -0
- data/CHANGELOG.org +15 -0
- data/LICENSE.txt +674 -0
- data/Rakefile +11 -2
- data/bin/czindexer +46 -39
- data/bin/czsearch +85 -4
- data/code_zauker.gemspec +1 -0
- data/doc/CodeZauker.html +42 -13
- data/doc/CodeZauker/FileScanner.html +373 -183
- data/doc/CodeZauker/Util.html +360 -0
- data/doc/Grep.html +344 -0
- data/doc/_index.html +31 -3
- data/doc/class_list.html +1 -1
- data/doc/frames.html +1 -1
- data/doc/index.html +31 -3
- data/doc/method_list.html +48 -0
- data/doc/top-level-namespace.html +3 -3
- data/lib/code_zauker.rb +182 -41
- data/lib/code_zauker/constants.rb +19 -7
- data/lib/code_zauker/grep.rb +17 -13
- data/lib/code_zauker/version.rb +1 -1
- data/readme.org +19 -8
- data/test/fixture/TEST_LICENSE.txt +0 -970
- data/test/fixture/kurukku.txt +3 -1
- data/test/fixture/testArchive.zip +0 -0
- data/test/test_search.rb +87 -12
- metadata +25 -8
@@ -0,0 +1,360 @@
|
|
1
|
+
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
2
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
3
|
+
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
4
|
+
<head>
|
5
|
+
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
6
|
+
<title>
|
7
|
+
Class: CodeZauker::Util
|
8
|
+
|
9
|
+
— Code Zauker 0.0.3 Documentation
|
10
|
+
|
11
|
+
</title>
|
12
|
+
|
13
|
+
<link rel="stylesheet" href="../css/style.css" type="text/css" media="screen" charset="utf-8" />
|
14
|
+
|
15
|
+
<link rel="stylesheet" href="../css/common.css" type="text/css" media="screen" charset="utf-8" />
|
16
|
+
|
17
|
+
<script type="text/javascript" charset="utf-8">
|
18
|
+
relpath = '..';
|
19
|
+
if (relpath != '') relpath += '/';
|
20
|
+
</script>
|
21
|
+
|
22
|
+
<script type="text/javascript" charset="utf-8" src="../js/jquery.js"></script>
|
23
|
+
|
24
|
+
<script type="text/javascript" charset="utf-8" src="../js/app.js"></script>
|
25
|
+
|
26
|
+
|
27
|
+
</head>
|
28
|
+
<body>
|
29
|
+
<script type="text/javascript" charset="utf-8">
|
30
|
+
if (window.top.frames.main) document.body.className = 'frames';
|
31
|
+
</script>
|
32
|
+
|
33
|
+
<div id="header">
|
34
|
+
<div id="menu">
|
35
|
+
|
36
|
+
<a href="../_index.html">Index (U)</a> »
|
37
|
+
<span class='title'><span class='object_link'><a href="../CodeZauker.html" title="CodeZauker (module)">CodeZauker</a></span></span>
|
38
|
+
»
|
39
|
+
<span class="title">Util</span>
|
40
|
+
|
41
|
+
|
42
|
+
<div class="noframes"><span class="title">(</span><a href="." target="_top">no frames</a><span class="title">)</span></div>
|
43
|
+
</div>
|
44
|
+
|
45
|
+
<div id="search">
|
46
|
+
|
47
|
+
<a id="class_list_link" href="#">Class List</a>
|
48
|
+
|
49
|
+
<a id="method_list_link" href="#">Method List</a>
|
50
|
+
|
51
|
+
<a id="file_list_link" href="#">File List</a>
|
52
|
+
|
53
|
+
</div>
|
54
|
+
<div class="clear"></div>
|
55
|
+
</div>
|
56
|
+
|
57
|
+
<iframe id="search_frame"></iframe>
|
58
|
+
|
59
|
+
<div id="content"><h1>Class: CodeZauker::Util
|
60
|
+
|
61
|
+
|
62
|
+
|
63
|
+
</h1>
|
64
|
+
|
65
|
+
<dl class="box">
|
66
|
+
|
67
|
+
<dt class="r1">Inherits:</dt>
|
68
|
+
<dd class="r1">
|
69
|
+
<span class="inheritName">Object</span>
|
70
|
+
|
71
|
+
<ul class="fullTree">
|
72
|
+
<li>Object</li>
|
73
|
+
|
74
|
+
<li class="next">CodeZauker::Util</li>
|
75
|
+
|
76
|
+
</ul>
|
77
|
+
<a href="#" class="inheritanceTree">show all</a>
|
78
|
+
|
79
|
+
</dd>
|
80
|
+
|
81
|
+
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
|
86
|
+
|
87
|
+
|
88
|
+
|
89
|
+
<dt class="r2 last">Defined in:</dt>
|
90
|
+
<dd class="r2 last">lib/code_zauker.rb</dd>
|
91
|
+
|
92
|
+
</dl>
|
93
|
+
<div class="clear"></div>
|
94
|
+
|
95
|
+
<h2>Overview</h2><div class="docstring">
|
96
|
+
<div class="discussion">
|
97
|
+
|
98
|
+
<h1>Basic utility class</h1>
|
99
|
+
|
100
|
+
|
101
|
+
</div>
|
102
|
+
</div>
|
103
|
+
<div class="tags">
|
104
|
+
|
105
|
+
|
106
|
+
</div>
|
107
|
+
|
108
|
+
|
109
|
+
|
110
|
+
|
111
|
+
|
112
|
+
<h2>
|
113
|
+
Instance Method Summary
|
114
|
+
<small>(<a href="#" class="summary_toggle">collapse</a>)</small>
|
115
|
+
</h2>
|
116
|
+
|
117
|
+
<ul class="summary">
|
118
|
+
|
119
|
+
<li class="public ">
|
120
|
+
<span class="summary_signature">
|
121
|
+
|
122
|
+
<a href="#ensureUTF8-instance_method" title="#ensureUTF8 (instance method)">- (Object) <strong>ensureUTF8</strong>(untrusted_string) </a>
|
123
|
+
|
124
|
+
|
125
|
+
|
126
|
+
</span>
|
127
|
+
|
128
|
+
|
129
|
+
|
130
|
+
|
131
|
+
|
132
|
+
|
133
|
+
|
134
|
+
|
135
|
+
<span class="summary_desc"><div class='inline'>
|
136
|
+
<h1>Ensure Data are correctly imported</h1>
|
137
|
+
|
138
|
+
<p><a
|
139
|
+
href="http://blog.grayproductions.net/articles/ruby_19s_string">blog.grayproductions.net/articles/ruby_19s_string</a>
|
140
|
+
This code try to "guess" the right encoding switching to ISO-8859-1 if
|
141
|
+
UTF-8 is not valid.</p>
|
142
|
+
</div></span>
|
143
|
+
|
144
|
+
</li>
|
145
|
+
|
146
|
+
|
147
|
+
<li class="public ">
|
148
|
+
<span class="summary_signature">
|
149
|
+
|
150
|
+
<a href="#mixCase-instance_method" title="#mixCase (instance method)">- (Object) <strong>mixCase</strong>(trigram) </a>
|
151
|
+
|
152
|
+
|
153
|
+
|
154
|
+
</span>
|
155
|
+
|
156
|
+
|
157
|
+
|
158
|
+
|
159
|
+
|
160
|
+
|
161
|
+
|
162
|
+
|
163
|
+
<span class="summary_desc"><div class='inline'>
|
164
|
+
<p>Compute all the possible case-mixed trigrams It works for every string size
|
165
|
+
TODO: Very bad implementation, need improvements.</p>
|
166
|
+
</div></span>
|
167
|
+
|
168
|
+
</li>
|
169
|
+
|
170
|
+
|
171
|
+
</ul>
|
172
|
+
|
173
|
+
|
174
|
+
|
175
|
+
|
176
|
+
<div id="instance_method_details" class="method_details_list">
|
177
|
+
<h2>Instance Method Details</h2>
|
178
|
+
|
179
|
+
|
180
|
+
<div class="method_details first">
|
181
|
+
<p class="signature first" id="ensureUTF8-instance_method">
|
182
|
+
|
183
|
+
- (<tt>Object</tt>) <strong>ensureUTF8</strong>(untrusted_string)
|
184
|
+
|
185
|
+
|
186
|
+
|
187
|
+
</p><div class="docstring">
|
188
|
+
<div class="discussion">
|
189
|
+
|
190
|
+
<h1>Ensure Data are correctly imported</h1>
|
191
|
+
|
192
|
+
<p><a
|
193
|
+
href="http://blog.grayproductions.net/articles/ruby_19s_string">blog.grayproductions.net/articles/ruby_19s_string</a>
|
194
|
+
This code try to "guess" the right encoding switching to ISO-8859-1 if
|
195
|
+
UTF-8 is not valid. Tipical use case: an italian source code wronlgy
|
196
|
+
interpreted as a UTF-8 whereas it is a ISO-8859 windows code.</p>
|
197
|
+
|
198
|
+
|
199
|
+
</div>
|
200
|
+
</div>
|
201
|
+
<div class="tags">
|
202
|
+
|
203
|
+
|
204
|
+
</div><table class="source_code">
|
205
|
+
<tr>
|
206
|
+
<td>
|
207
|
+
<pre class="lines">
|
208
|
+
|
209
|
+
|
210
|
+
56
|
211
|
+
57
|
212
|
+
58
|
213
|
+
59
|
214
|
+
60
|
215
|
+
61
|
216
|
+
62
|
217
|
+
63
|
218
|
+
64
|
219
|
+
65
|
220
|
+
66
|
221
|
+
67
|
222
|
+
68
|
223
|
+
69
|
224
|
+
70
|
225
|
+
71
|
226
|
+
72
|
227
|
+
73</pre>
|
228
|
+
</td>
|
229
|
+
<td>
|
230
|
+
<pre class="code"><span class="info file"># File 'lib/code_zauker.rb', line 56</span>
|
231
|
+
|
232
|
+
<span class='kw'>def</span> <span class='id identifier rubyid_ensureUTF8'>ensureUTF8</span><span class='lparen'>(</span><span class='id identifier rubyid_untrusted_string'>untrusted_string</span><span class='rparen'>)</span>
|
233
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_untrusted_string'>untrusted_string</span><span class='period'>.</span><span class='id identifier rubyid_valid_encoding?'>valid_encoding?</span><span class='lparen'>(</span><span class='rparen'>)</span><span class='op'>==</span><span class='kw'>false</span>
|
234
|
+
<span class='comment'>#puts "DEBUG Trouble on #{untrusted_string}"
|
235
|
+
</span> <span class='id identifier rubyid_untrusted_string'>untrusted_string</span><span class='period'>.</span><span class='id identifier rubyid_force_encoding'>force_encoding</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>ISO-8859-1</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
236
|
+
<span class='comment'># We try ISO-8859-1 tipical windows
|
237
|
+
</span> <span class='kw'>begin</span>
|
238
|
+
<span class='id identifier rubyid_valid_string'>valid_string</span><span class='op'>=</span><span class='id identifier rubyid_untrusted_string'>untrusted_string</span><span class='period'>.</span><span class='id identifier rubyid_encode'>encode</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>UTF-8</span><span class='tstring_end'>"</span></span><span class='comma'>,</span> <span class='lbrace'>{</span> <span class='symbol'>:undef</span> <span class='op'>=></span><span class='symbol'>:replace</span><span class='comma'>,</span> <span class='symbol'>:invalid</span> <span class='op'>=></span> <span class='symbol'>:replace</span><span class='rbrace'>}</span> <span class='rparen'>)</span>
|
239
|
+
<span class='kw'>rescue</span> <span class='const'>Encoding</span><span class='op'>::</span><span class='const'>InvalidByteSequenceError</span> <span class='op'>=></span> <span class='id identifier rubyid_e'>e</span>
|
240
|
+
<span class='id identifier rubyid_raise'>raise</span> <span class='id identifier rubyid_e'>e</span>
|
241
|
+
<span class='kw'>end</span>
|
242
|
+
<span class='comment'># if valid_string != untrusted_string
|
243
|
+
</span> <span class='comment'># puts "CONVERTED #{valid_string} Works?#{valid_string.valid_encoding?}"
|
244
|
+
</span> <span class='comment'># end
|
245
|
+
</span> <span class='kw'>return</span> <span class='id identifier rubyid_valid_string'>valid_string</span>
|
246
|
+
<span class='kw'>else</span>
|
247
|
+
<span class='kw'>return</span> <span class='id identifier rubyid_untrusted_string'>untrusted_string</span>
|
248
|
+
<span class='kw'>end</span>
|
249
|
+
<span class='kw'>end</span></pre>
|
250
|
+
</td>
|
251
|
+
</tr>
|
252
|
+
</table>
|
253
|
+
</div>
|
254
|
+
|
255
|
+
<div class="method_details ">
|
256
|
+
<p class="signature " id="mixCase-instance_method">
|
257
|
+
|
258
|
+
- (<tt>Object</tt>) <strong>mixCase</strong>(trigram)
|
259
|
+
|
260
|
+
|
261
|
+
|
262
|
+
</p><div class="docstring">
|
263
|
+
<div class="discussion">
|
264
|
+
|
265
|
+
<p>Compute all the possible case-mixed trigrams It works for every string size
|
266
|
+
TODO: Very bad implementation, need improvements</p>
|
267
|
+
|
268
|
+
|
269
|
+
</div>
|
270
|
+
</div>
|
271
|
+
<div class="tags">
|
272
|
+
|
273
|
+
|
274
|
+
</div><table class="source_code">
|
275
|
+
<tr>
|
276
|
+
<td>
|
277
|
+
<pre class="lines">
|
278
|
+
|
279
|
+
|
280
|
+
19
|
281
|
+
20
|
282
|
+
21
|
283
|
+
22
|
284
|
+
23
|
285
|
+
24
|
286
|
+
25
|
287
|
+
26
|
288
|
+
27
|
289
|
+
28
|
290
|
+
29
|
291
|
+
30
|
292
|
+
31
|
293
|
+
32
|
294
|
+
33
|
295
|
+
34
|
296
|
+
35
|
297
|
+
36
|
298
|
+
37
|
299
|
+
38
|
300
|
+
39
|
301
|
+
40
|
302
|
+
41
|
303
|
+
42
|
304
|
+
43
|
305
|
+
44
|
306
|
+
45
|
307
|
+
46
|
308
|
+
47
|
309
|
+
48</pre>
|
310
|
+
</td>
|
311
|
+
<td>
|
312
|
+
<pre class="code"><span class="info file"># File 'lib/code_zauker.rb', line 19</span>
|
313
|
+
|
314
|
+
<span class='kw'>def</span> <span class='id identifier rubyid_mixCase'>mixCase</span><span class='lparen'>(</span><span class='id identifier rubyid_trigram'>trigram</span><span class='rparen'>)</span>
|
315
|
+
<span class='id identifier rubyid_caseMixedElements'>caseMixedElements</span><span class='op'>=</span><span class='lbracket'>[</span><span class='rbracket'>]</span>
|
316
|
+
<span class='id identifier rubyid_lx'>lx</span><span class='op'>=</span><span class='id identifier rubyid_trigram'>trigram</span><span class='period'>.</span><span class='id identifier rubyid_length'>length</span>
|
317
|
+
<span class='id identifier rubyid_combos'>combos</span><span class='op'>=</span><span class='int'>2</span><span class='op'>**</span><span class='id identifier rubyid_lx'>lx</span>
|
318
|
+
<span class='id identifier rubyid_startString'>startString</span><span class='op'>=</span><span class='id identifier rubyid_trigram'>trigram</span><span class='period'>.</span><span class='id identifier rubyid_downcase'>downcase</span>
|
319
|
+
<span class='comment'>#puts "Combos... 1..#{combos}... #{startString}"
|
320
|
+
</span> <span class='kw'>for</span> <span class='id identifier rubyid_c'>c</span> <span class='kw'>in</span> <span class='int'>0</span><span class='op'>..</span><span class='lparen'>(</span><span class='id identifier rubyid_combos'>combos</span><span class='op'>-</span><span class='int'>1</span><span class='rparen'>)</span> <span class='kw'>do</span>
|
321
|
+
<span class='comment'># Make binary
|
322
|
+
</span> <span class='id identifier rubyid_maskForStuff'>maskForStuff</span><span class='op'>=</span><span class='id identifier rubyid_c'>c</span><span class='period'>.</span><span class='id identifier rubyid_to_s'>to_s</span><span class='lparen'>(</span><span class='int'>2</span><span class='rparen'>)</span>
|
323
|
+
<span class='id identifier rubyid_p'>p</span><span class='op'>=</span><span class='int'>0</span>
|
324
|
+
<span class='comment'>#puts maskForStuff
|
325
|
+
</span> <span class='id identifier rubyid_currentMix'>currentMix</span><span class='op'>=</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_end'>"</span></span>
|
326
|
+
<span class='comment'># Pad it
|
327
|
+
</span> <span class='kw'>if</span> <span class='id identifier rubyid_maskForStuff'>maskForStuff</span><span class='period'>.</span><span class='id identifier rubyid_length'>length</span> <span class='op'><</span> <span class='id identifier rubyid_lx'>lx</span>
|
328
|
+
<span class='id identifier rubyid_maskForStuff'>maskForStuff</span> <span class='op'>=</span> <span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>0</span><span class='tstring_end'>"</span></span><span class='op'>*</span><span class='lparen'>(</span><span class='id identifier rubyid_lx'>lx</span><span class='op'>-</span><span class='id identifier rubyid_maskForStuff'>maskForStuff</span><span class='period'>.</span><span class='id identifier rubyid_length'>length</span><span class='rparen'>)</span><span class='rparen'>)</span> <span class='op'>+</span><span class='id identifier rubyid_maskForStuff'>maskForStuff</span>
|
329
|
+
<span class='kw'>end</span>
|
330
|
+
<span class='id identifier rubyid_maskForStuff'>maskForStuff</span><span class='period'>.</span><span class='id identifier rubyid_each_char'>each_char</span> <span class='lbrace'>{</span> <span class='op'>|</span> <span class='id identifier rubyid_x'>x</span> <span class='op'>|</span>
|
331
|
+
<span class='comment'>#putc x
|
332
|
+
</span> <span class='kw'>if</span> <span class='id identifier rubyid_x'>x</span><span class='op'>==</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>1</span><span class='tstring_end'>"</span></span>
|
333
|
+
<span class='id identifier rubyid_currentMix'>currentMix</span> <span class='op'>+=</span><span class='id identifier rubyid_startString'>startString</span><span class='lbracket'>[</span><span class='id identifier rubyid_p'>p</span><span class='rbracket'>]</span><span class='period'>.</span><span class='id identifier rubyid_upcase'>upcase</span>
|
334
|
+
<span class='kw'>else</span>
|
335
|
+
<span class='id identifier rubyid_currentMix'>currentMix</span> <span class='op'>+=</span><span class='id identifier rubyid_startString'>startString</span><span class='lbracket'>[</span><span class='id identifier rubyid_p'>p</span><span class='rbracket'>]</span><span class='period'>.</span><span class='id identifier rubyid_downcase'>downcase</span>
|
336
|
+
<span class='kw'>end</span>
|
337
|
+
<span class='comment'>#puts currentMix
|
338
|
+
</span> <span class='id identifier rubyid_p'>p</span><span class='op'>+=</span><span class='int'>1</span>
|
339
|
+
<span class='rbrace'>}</span>
|
340
|
+
<span class='id identifier rubyid_caseMixedElements'>caseMixedElements</span><span class='period'>.</span><span class='id identifier rubyid_push'>push</span><span class='lparen'>(</span><span class='id identifier rubyid_currentMix'>currentMix</span><span class='rparen'>)</span>
|
341
|
+
<span class='kw'>end</span>
|
342
|
+
<span class='kw'>return</span> <span class='id identifier rubyid_caseMixedElements'>caseMixedElements</span>
|
343
|
+
<span class='kw'>end</span></pre>
|
344
|
+
</td>
|
345
|
+
</tr>
|
346
|
+
</table>
|
347
|
+
</div>
|
348
|
+
|
349
|
+
</div>
|
350
|
+
|
351
|
+
</div>
|
352
|
+
|
353
|
+
<div id="footer">
|
354
|
+
Generated on Fri Feb 3 17:18:43 2012 by
|
355
|
+
<a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
|
356
|
+
0.7.4 (ruby-1.9.3).
|
357
|
+
</div>
|
358
|
+
|
359
|
+
</body>
|
360
|
+
</html>
|
data/doc/Grep.html
ADDED
@@ -0,0 +1,344 @@
|
|
1
|
+
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
2
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
3
|
+
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
4
|
+
<head>
|
5
|
+
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
6
|
+
<title>
|
7
|
+
Module: Grep
|
8
|
+
|
9
|
+
— Code Zauker 0.0.3 Documentation
|
10
|
+
|
11
|
+
</title>
|
12
|
+
|
13
|
+
<link rel="stylesheet" href="css/style.css" type="text/css" media="screen" charset="utf-8" />
|
14
|
+
|
15
|
+
<link rel="stylesheet" href="css/common.css" type="text/css" media="screen" charset="utf-8" />
|
16
|
+
|
17
|
+
<script type="text/javascript" charset="utf-8">
|
18
|
+
relpath = '';
|
19
|
+
if (relpath != '') relpath += '/';
|
20
|
+
</script>
|
21
|
+
|
22
|
+
<script type="text/javascript" charset="utf-8" src="js/jquery.js"></script>
|
23
|
+
|
24
|
+
<script type="text/javascript" charset="utf-8" src="js/app.js"></script>
|
25
|
+
|
26
|
+
|
27
|
+
</head>
|
28
|
+
<body>
|
29
|
+
<script type="text/javascript" charset="utf-8">
|
30
|
+
if (window.top.frames.main) document.body.className = 'frames';
|
31
|
+
</script>
|
32
|
+
|
33
|
+
<div id="header">
|
34
|
+
<div id="menu">
|
35
|
+
|
36
|
+
<a href="_index.html">Index (G)</a> »
|
37
|
+
|
38
|
+
|
39
|
+
<span class="title">Grep</span>
|
40
|
+
|
41
|
+
|
42
|
+
<div class="noframes"><span class="title">(</span><a href="." target="_top">no frames</a><span class="title">)</span></div>
|
43
|
+
</div>
|
44
|
+
|
45
|
+
<div id="search">
|
46
|
+
|
47
|
+
<a id="class_list_link" href="#">Class List</a>
|
48
|
+
|
49
|
+
<a id="method_list_link" href="#">Method List</a>
|
50
|
+
|
51
|
+
<a id="file_list_link" href="#">File List</a>
|
52
|
+
|
53
|
+
</div>
|
54
|
+
<div class="clear"></div>
|
55
|
+
</div>
|
56
|
+
|
57
|
+
<iframe id="search_frame"></iframe>
|
58
|
+
|
59
|
+
<div id="content"><h1>Module: Grep
|
60
|
+
|
61
|
+
|
62
|
+
|
63
|
+
</h1>
|
64
|
+
|
65
|
+
<dl class="box">
|
66
|
+
|
67
|
+
|
68
|
+
|
69
|
+
|
70
|
+
|
71
|
+
|
72
|
+
|
73
|
+
|
74
|
+
<dt class="r1 last">Defined in:</dt>
|
75
|
+
<dd class="r1 last">lib/code_zauker/grep.rb</dd>
|
76
|
+
|
77
|
+
</dl>
|
78
|
+
<div class="clear"></div>
|
79
|
+
|
80
|
+
|
81
|
+
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
|
86
|
+
<h2>
|
87
|
+
Instance Method Summary
|
88
|
+
<small>(<a href="#" class="summary_toggle">collapse</a>)</small>
|
89
|
+
</h2>
|
90
|
+
|
91
|
+
<ul class="summary">
|
92
|
+
|
93
|
+
<li class="public ">
|
94
|
+
<span class="summary_signature">
|
95
|
+
|
96
|
+
<a href="#grep-instance_method" title="#grep (instance method)">- (Object) <strong>grep</strong>(file, pattern, pre_context = 0, post_context = 0, print_filename = true) </a>
|
97
|
+
|
98
|
+
|
99
|
+
|
100
|
+
</span>
|
101
|
+
|
102
|
+
|
103
|
+
|
104
|
+
|
105
|
+
|
106
|
+
|
107
|
+
|
108
|
+
|
109
|
+
<span class="summary_desc"><div class='inline'>
|
110
|
+
<p>Grep works like a shell grep.</p>
|
111
|
+
</div></span>
|
112
|
+
|
113
|
+
</li>
|
114
|
+
|
115
|
+
|
116
|
+
</ul>
|
117
|
+
|
118
|
+
|
119
|
+
|
120
|
+
|
121
|
+
<div id="instance_method_details" class="method_details_list">
|
122
|
+
<h2>Instance Method Details</h2>
|
123
|
+
|
124
|
+
|
125
|
+
<div class="method_details first">
|
126
|
+
<p class="signature first" id="grep-instance_method">
|
127
|
+
|
128
|
+
- (<tt>Object</tt>) <strong>grep</strong>(file, pattern, pre_context = 0, post_context = 0, print_filename = true)
|
129
|
+
|
130
|
+
|
131
|
+
|
132
|
+
</p><div class="docstring">
|
133
|
+
<div class="discussion">
|
134
|
+
|
135
|
+
<p>Grep works like a shell grep. `file' can be either a string, containing the
|
136
|
+
name of a file to load and handle, or an IO object (such as $stdin) to deal
|
137
|
+
with. `pattern' can be either a string or Regexp object which contains a
|
138
|
+
pattern. Patterns as strings treat no part of the string as `special', such
|
139
|
+
as '.' or '?' in a regex. `pre_context' and `post_context' determine the
|
140
|
+
amount of lines to return that came before or after the content that was
|
141
|
+
matched, respectively. If there are overlaps in the context, no duplicates
|
142
|
+
will be printed.</p>
|
143
|
+
|
144
|
+
|
145
|
+
</div>
|
146
|
+
</div>
|
147
|
+
<div class="tags">
|
148
|
+
|
149
|
+
|
150
|
+
</div><table class="source_code">
|
151
|
+
<tr>
|
152
|
+
<td>
|
153
|
+
<pre class="lines">
|
154
|
+
|
155
|
+
|
156
|
+
58
|
157
|
+
59
|
158
|
+
60
|
159
|
+
61
|
160
|
+
62
|
161
|
+
63
|
162
|
+
64
|
163
|
+
65
|
164
|
+
66
|
165
|
+
67
|
166
|
+
68
|
167
|
+
69
|
168
|
+
70
|
169
|
+
71
|
170
|
+
72
|
171
|
+
73
|
172
|
+
74
|
173
|
+
75
|
174
|
+
76
|
175
|
+
77
|
176
|
+
78
|
177
|
+
79
|
178
|
+
80
|
179
|
+
81
|
180
|
+
82
|
181
|
+
83
|
182
|
+
84
|
183
|
+
85
|
184
|
+
86
|
185
|
+
87
|
186
|
+
88
|
187
|
+
89
|
188
|
+
90
|
189
|
+
91
|
190
|
+
92
|
191
|
+
93
|
192
|
+
94
|
193
|
+
95
|
194
|
+
96
|
195
|
+
97
|
196
|
+
98
|
197
|
+
99
|
198
|
+
100
|
199
|
+
101
|
200
|
+
102
|
201
|
+
103
|
202
|
+
104
|
203
|
+
105
|
204
|
+
106
|
205
|
+
107
|
206
|
+
108
|
207
|
+
109
|
208
|
+
110
|
209
|
+
111
|
210
|
+
112
|
211
|
+
113
|
212
|
+
114
|
213
|
+
115
|
214
|
+
116
|
215
|
+
117
|
216
|
+
118
|
217
|
+
119
|
218
|
+
120
|
219
|
+
121
|
220
|
+
122
|
221
|
+
123
|
222
|
+
124
|
223
|
+
125
|
224
|
+
126
|
225
|
+
127
|
226
|
+
128
|
227
|
+
129
|
228
|
+
130
|
229
|
+
131
|
230
|
+
132
|
231
|
+
133
|
232
|
+
134
|
233
|
+
135
|
234
|
+
136
|
235
|
+
137
|
236
|
+
138
|
237
|
+
139
|
238
|
+
140
|
239
|
+
141</pre>
|
240
|
+
</td>
|
241
|
+
<td>
|
242
|
+
<pre class="code"><span class="info file"># File 'lib/code_zauker/grep.rb', line 58</span>
|
243
|
+
|
244
|
+
<span class='kw'>def</span> <span class='id identifier rubyid_grep'>grep</span><span class='lparen'>(</span><span class='id identifier rubyid_file'>file</span><span class='comma'>,</span> <span class='id identifier rubyid_pattern'>pattern</span><span class='comma'>,</span> <span class='id identifier rubyid_pre_context'>pre_context</span><span class='op'>=</span><span class='int'>0</span><span class='comma'>,</span> <span class='id identifier rubyid_post_context'>post_context</span><span class='op'>=</span><span class='int'>0</span><span class='comma'>,</span> <span class='id identifier rubyid_print_filename'>print_filename</span><span class='op'>=</span><span class='kw'>true</span><span class='rparen'>)</span>
|
245
|
+
<span class='id identifier rubyid_currentline'>currentline</span><span class='op'>=</span><span class='int'>0</span>
|
246
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_file'>file</span><span class='period'>.</span><span class='id identifier rubyid_kind_of?'>kind_of?</span> <span class='const'>String</span>
|
247
|
+
<span class='id identifier rubyid_fileName'>fileName</span><span class='op'>=</span><span class='id identifier rubyid_file'>file</span>
|
248
|
+
<span class='id identifier rubyid_file'>file</span> <span class='op'>=</span> <span class='const'>File</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='id identifier rubyid_file'>file</span><span class='comma'>,</span> <span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>r</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
249
|
+
<span class='kw'>else</span>
|
250
|
+
<span class='id identifier rubyid_fileName'>fileName</span><span class='op'>=</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_end'>"</span></span>
|
251
|
+
<span class='kw'>end</span>
|
252
|
+
|
253
|
+
<span class='kw'>if</span> <span class='op'>!</span> <span class='id identifier rubyid_file'>file</span><span class='period'>.</span><span class='id identifier rubyid_kind_of?'>kind_of?</span> <span class='const'>IO</span>
|
254
|
+
<span class='id identifier rubyid_throw'>throw</span> <span class='const'>IOError</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>File must be the name of an existing file or IO object</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
255
|
+
<span class='kw'>end</span>
|
256
|
+
|
257
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_pattern'>pattern</span><span class='period'>.</span><span class='id identifier rubyid_kind_of?'>kind_of?</span> <span class='const'>String</span>
|
258
|
+
<span class='id identifier rubyid_pattern'>pattern</span> <span class='op'>=</span> <span class='tstring'><span class='regexp_beg'>/</span><span class='embexpr_beg'>#{</span><span class='const'>Regexp</span><span class='period'>.</span><span class='id identifier rubyid_escape'>escape</span><span class='lparen'>(</span><span class='id identifier rubyid_pattern'>pattern</span><span class='rparen'>)</span><span class='rbrace'>}</span><span class='regexp_end'>/</span></span>
|
259
|
+
<span class='kw'>end</span>
|
260
|
+
|
261
|
+
<span class='kw'>if</span> <span class='op'>!</span> <span class='id identifier rubyid_pattern'>pattern</span><span class='period'>.</span><span class='id identifier rubyid_kind_of?'>kind_of?</span> <span class='const'>Regexp</span>
|
262
|
+
<span class='id identifier rubyid_throw'>throw</span> <span class='const'>StandardError</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>Pattern must be string or regexp</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
263
|
+
<span class='kw'>end</span>
|
264
|
+
|
265
|
+
<span class='id identifier rubyid_cache'>cache</span> <span class='op'>=</span> <span class='lbracket'>[</span><span class='rbracket'>]</span>
|
266
|
+
<span class='id identifier rubyid_lines'>lines</span> <span class='op'>=</span> <span class='lbracket'>[</span><span class='rbracket'>]</span>
|
267
|
+
|
268
|
+
<span class='id identifier rubyid_util'>util</span><span class='op'>=</span><span class='const'>CodeZauker</span><span class='op'>::</span><span class='const'>Util</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='rparen'>)</span>
|
269
|
+
|
270
|
+
<span class='id identifier rubyid_loop'>loop</span> <span class='kw'>do</span>
|
271
|
+
<span class='kw'>begin</span>
|
272
|
+
<span class='id identifier rubyid_line'>line</span> <span class='op'>=</span> <span class='id identifier rubyid_util'>util</span><span class='period'>.</span><span class='id identifier rubyid_ensureUTF8'>ensureUTF8</span><span class='lparen'>(</span><span class='id identifier rubyid_file'>file</span><span class='period'>.</span><span class='id identifier rubyid_readline'>readline</span><span class='rparen'>)</span>
|
273
|
+
|
274
|
+
<span class='id identifier rubyid_currentline'>currentline</span> <span class='op'>+=</span><span class='int'>1</span>
|
275
|
+
<span class='id identifier rubyid_cache'>cache</span><span class='period'>.</span><span class='id identifier rubyid_shift'>shift</span> <span class='kw'>unless</span> <span class='id identifier rubyid_cache'>cache</span><span class='period'>.</span><span class='id identifier rubyid_length'>length</span> <span class='op'><</span> <span class='id identifier rubyid_pre_context'>pre_context</span>
|
276
|
+
|
277
|
+
<span class='id identifier rubyid_cache'>cache</span><span class='period'>.</span><span class='id identifier rubyid_push'>push</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_currentline'>currentline</span><span class='rbrace'>}</span><span class='tstring_content'>:</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_line'>line</span><span class='rbrace'>}</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
278
|
+
|
279
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_line'>line</span> <span class='op'>=~</span> <span class='id identifier rubyid_pattern'>pattern</span>
|
280
|
+
<span class='id identifier rubyid_lines'>lines</span> <span class='op'>+=</span> <span class='id identifier rubyid_cache'>cache</span>
|
281
|
+
<span class='id identifier rubyid_cache'>cache</span> <span class='op'>=</span> <span class='lbracket'>[</span><span class='rbracket'>]</span>
|
282
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_post_context'>post_context</span> <span class='op'>></span> <span class='int'>0</span>
|
283
|
+
<span class='id identifier rubyid_post_context'>post_context</span><span class='period'>.</span><span class='id identifier rubyid_times'>times</span> <span class='kw'>do</span>
|
284
|
+
<span class='kw'>begin</span>
|
285
|
+
<span class='id identifier rubyid_utf8line'>utf8line</span><span class='op'>=</span><span class='id identifier rubyid_util'>util</span><span class='period'>.</span><span class='id identifier rubyid_ensureUTF8'>ensureUTF8</span><span class='lparen'>(</span><span class='id identifier rubyid_file'>file</span><span class='period'>.</span><span class='id identifier rubyid_readline'>readline</span><span class='rparen'>)</span>
|
286
|
+
<span class='id identifier rubyid_lines'>lines</span><span class='period'>.</span><span class='id identifier rubyid_push'>push</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_currentline'>currentline</span><span class='rbrace'>}</span><span class='tstring_content'>:</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_utf8line'>utf8line</span><span class='rbrace'>}</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
287
|
+
<span class='id identifier rubyid_currentline'>currentline</span> <span class='op'>+=</span><span class='int'>1</span>
|
288
|
+
<span class='kw'>rescue</span> <span class='const'>IOError</span> <span class='op'>=></span> <span class='id identifier rubyid_e'>e</span>
|
289
|
+
<span class='kw'>break</span>
|
290
|
+
<span class='kw'>end</span>
|
291
|
+
<span class='kw'>end</span>
|
292
|
+
<span class='kw'>end</span>
|
293
|
+
<span class='kw'>end</span>
|
294
|
+
<span class='kw'>rescue</span> <span class='const'>IOError</span> <span class='op'>=></span> <span class='id identifier rubyid_e'>e</span>
|
295
|
+
<span class='kw'>break</span>
|
296
|
+
<span class='kw'>rescue</span> <span class='const'>ArgumentError</span> <span class='op'>=></span><span class='id identifier rubyid_e2'>e2</span>
|
297
|
+
<span class='comment'># Rethrow a probably UTF-8 fatal error
|
298
|
+
</span> <span class='id identifier rubyid_puts'>puts</span> <span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>Pattern Matching failed on \n\t</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_fileName'>fileName</span><span class='rbrace'>}</span><span class='tstring_content'>\n\tLine:</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_line'>line</span><span class='rbrace'>}</span><span class='tstring_end'>"</span></span>
|
299
|
+
<span class='id identifier rubyid_puts'>puts</span> <span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>Encoding of line:</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_line'>line</span><span class='period'>.</span><span class='id identifier rubyid_encoding'>encoding</span><span class='period'>.</span><span class='id identifier rubyid_name'>name</span><span class='rbrace'>}</span><span class='tstring_content'> Valid? </span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_line'>line</span><span class='period'>.</span><span class='id identifier rubyid_valid_encoding?'>valid_encoding?</span><span class='rbrace'>}</span><span class='tstring_end'>"</span></span>
|
300
|
+
<span class='comment'>#raise e2
|
301
|
+
</span> <span class='kw'>end</span>
|
302
|
+
<span class='kw'>end</span>
|
303
|
+
|
304
|
+
|
305
|
+
<span class='id identifier rubyid_file'>file</span><span class='period'>.</span><span class='id identifier rubyid_each_line'>each_line</span> <span class='kw'>do</span> <span class='op'>|</span><span class='id identifier rubyid_untrustedLine'>untrustedLine</span><span class='op'>|</span>
|
306
|
+
<span class='id identifier rubyid_cache'>cache</span><span class='period'>.</span><span class='id identifier rubyid_shift'>shift</span> <span class='kw'>unless</span> <span class='id identifier rubyid_cache'>cache</span><span class='period'>.</span><span class='id identifier rubyid_length'>length</span> <span class='op'><</span> <span class='id identifier rubyid_pre_context'>pre_context</span>
|
307
|
+
<span class='id identifier rubyid_line'>line</span><span class='op'>=</span><span class='id identifier rubyid_util'>util</span><span class='period'>.</span><span class='id identifier rubyid_ensureUTF8'>ensureUTF8</span><span class='lparen'>(</span><span class='id identifier rubyid_untrustedLine'>untrustedLine</span><span class='rparen'>)</span>
|
308
|
+
<span class='id identifier rubyid_cache'>cache</span><span class='period'>.</span><span class='id identifier rubyid_push'>push</span><span class='lparen'>(</span><span class='id identifier rubyid_line'>line</span><span class='rparen'>)</span>
|
309
|
+
|
310
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_line'>line</span> <span class='op'>=~</span> <span class='id identifier rubyid_pattern'>pattern</span>
|
311
|
+
<span class='id identifier rubyid_lines'>lines</span> <span class='op'>+=</span> <span class='id identifier rubyid_cache'>cache</span>
|
312
|
+
<span class='kw'>if</span> <span class='id identifier rubyid_post_context'>post_context</span> <span class='op'>></span> <span class='int'>0</span>
|
313
|
+
<span class='id identifier rubyid_post_context'>post_context</span><span class='period'>.</span><span class='id identifier rubyid_times'>times</span> <span class='kw'>do</span>
|
314
|
+
<span class='kw'>begin</span>
|
315
|
+
<span class='id identifier rubyid_utf8line'>utf8line</span><span class='op'>=</span><span class='id identifier rubyid_util'>util</span><span class='period'>.</span><span class='id identifier rubyid_ensureUTF8'>ensureUTF8</span><span class='lparen'>(</span><span class='id identifier rubyid_file'>file</span><span class='period'>.</span><span class='id identifier rubyid_readline'>readline</span><span class='rparen'>)</span>
|
316
|
+
<span class='id identifier rubyid_lines'>lines</span><span class='period'>.</span><span class='id identifier rubyid_push'>push</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_currentline'>currentline</span><span class='rbrace'>}</span><span class='tstring_content'>:</span><span class='embexpr_beg'>#{</span><span class='id identifier rubyid_utf8line'>utf8line</span><span class='rbrace'>}</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
317
|
+
<span class='id identifier rubyid_currentline'>currentline</span> <span class='op'>+=</span><span class='int'>1</span>
|
318
|
+
<span class='kw'>rescue</span> <span class='const'>Exception</span> <span class='op'>=></span> <span class='id identifier rubyid_e'>e</span>
|
319
|
+
<span class='kw'>break</span>
|
320
|
+
<span class='kw'>end</span>
|
321
|
+
<span class='kw'>end</span>
|
322
|
+
<span class='kw'>end</span>
|
323
|
+
<span class='kw'>end</span>
|
324
|
+
<span class='kw'>end</span>
|
325
|
+
|
326
|
+
<span class='kw'>return</span> <span class='id identifier rubyid_lines'>lines</span>
|
327
|
+
<span class='kw'>end</span></pre>
|
328
|
+
</td>
|
329
|
+
</tr>
|
330
|
+
</table>
|
331
|
+
</div>
|
332
|
+
|
333
|
+
</div>
|
334
|
+
|
335
|
+
</div>
|
336
|
+
|
337
|
+
<div id="footer">
|
338
|
+
Generated on Fri Feb 3 17:18:44 2012 by
|
339
|
+
<a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
|
340
|
+
0.7.4 (ruby-1.9.3).
|
341
|
+
</div>
|
342
|
+
|
343
|
+
</body>
|
344
|
+
</html>
|