Show More
@@ -1,862 +1,862 b'' | |||
|
1 | 1 | """Analysis of text input into executable blocks. |
|
2 | 2 | |
|
3 | 3 | The main class in this module, :class:`InputSplitter`, is designed to break |
|
4 | 4 | input from either interactive, line-by-line environments or block-based ones, |
|
5 | 5 | into standalone blocks that can be executed by Python as 'single' statements |
|
6 | 6 | (thus triggering sys.displayhook). |
|
7 | 7 | |
|
8 | 8 | A companion, :class:`IPythonInputSplitter`, provides the same functionality but |
|
9 | 9 | with full support for the extended IPython syntax (magics, system calls, etc). |
|
10 | 10 | |
|
11 | 11 | For more details, see the class docstring below. |
|
12 | 12 | |
|
13 | 13 | Syntax Transformations |
|
14 | 14 | ---------------------- |
|
15 | 15 | |
|
16 | 16 | One of the main jobs of the code in this file is to apply all syntax |
|
17 | 17 | transformations that make up 'the IPython language', i.e. magics, shell |
|
18 | 18 | escapes, etc. All transformations should be implemented as *fully stateless* |
|
19 | 19 | entities, that simply take one line as their input and return a line. |
|
20 | 20 | Internally for implementation purposes they may be a normal function or a |
|
21 | 21 | callable object, but the only input they receive will be a single line and they |
|
22 | 22 | should only return a line, without holding any data-dependent state between |
|
23 | 23 | calls. |
|
24 | 24 | |
|
25 | 25 | As an example, the EscapedTransformer is a class so we can more clearly group |
|
26 | 26 | together the functionality of dispatching to individual functions based on the |
|
27 | 27 | starting escape character, but the only method for public use is its call |
|
28 | 28 | method. |
|
29 | 29 | |
|
30 | 30 | |
|
31 | 31 | ToDo |
|
32 | 32 | ---- |
|
33 | 33 | |
|
34 | 34 | - Should we make push() actually raise an exception once push_accepts_more() |
|
35 | 35 | returns False? |
|
36 | 36 | |
|
37 | 37 | - Naming cleanups. The tr_* names aren't the most elegant, though now they are |
|
38 | 38 | at least just attributes of a class so not really very exposed. |
|
39 | 39 | |
|
40 | 40 | - Think about the best way to support dynamic things: automagic, autocall, |
|
41 | 41 | macros, etc. |
|
42 | 42 | |
|
43 | 43 | - Think of a better heuristic for the application of the transforms in |
|
44 | 44 | IPythonInputSplitter.push() than looking at the buffer ending in ':'. Idea: |
|
45 | 45 | track indentation change events (indent, dedent, nothing) and apply them only |
|
46 | 46 | if the indentation went up, but not otherwise. |
|
47 | 47 | |
|
48 | 48 | - Think of the cleanest way for supporting user-specified transformations (the |
|
49 | 49 | user prefilters we had before). |
|
50 | 50 | |
|
51 | 51 | Authors |
|
52 | 52 | ------- |
|
53 | 53 | |
|
54 | 54 | * Fernando Perez |
|
55 | 55 | * Brian Granger |
|
56 | 56 | """ |
|
57 | 57 | #----------------------------------------------------------------------------- |
|
58 | 58 | # Copyright (C) 2010 The IPython Development Team |
|
59 | 59 | # |
|
60 | 60 | # Distributed under the terms of the BSD License. The full license is in |
|
61 | 61 | # the file COPYING, distributed as part of this software. |
|
62 | 62 | #----------------------------------------------------------------------------- |
|
63 | 63 | from __future__ import print_function |
|
64 | 64 | |
|
65 | 65 | #----------------------------------------------------------------------------- |
|
66 | 66 | # Imports |
|
67 | 67 | #----------------------------------------------------------------------------- |
|
68 | 68 | # stdlib |
|
69 | 69 | import ast |
|
70 | 70 | import codeop |
|
71 | 71 | import re |
|
72 | 72 | import sys |
|
73 | 73 | |
|
74 | 74 | # IPython modules |
|
75 | 75 | from IPython.utils.text import make_quoted_expr |
|
76 | 76 | |
|
77 | 77 | #----------------------------------------------------------------------------- |
|
78 | 78 | # Globals |
|
79 | 79 | #----------------------------------------------------------------------------- |
|
80 | 80 | |
|
81 | 81 | # The escape sequences that define the syntax transformations IPython will |
|
82 | 82 | # apply to user input. These can NOT be just changed here: many regular |
|
83 | 83 | # expressions and other parts of the code may use their hardcoded values, and |
|
84 | 84 | # for all intents and purposes they constitute the 'IPython syntax', so they |
|
85 | 85 | # should be considered fixed. |
|
86 | 86 | |
|
87 | 87 | ESC_SHELL = '!' # Send line to underlying system shell |
|
88 | 88 | ESC_SH_CAP = '!!' # Send line to system shell and capture output |
|
89 | 89 | ESC_HELP = '?' # Find information about object |
|
90 | 90 | ESC_HELP2 = '??' # Find extra-detailed information about object |
|
91 | 91 | ESC_MAGIC = '%' # Call magic function |
|
92 | 92 | ESC_QUOTE = ',' # Split args on whitespace, quote each as string and call |
|
93 | 93 | ESC_QUOTE2 = ';' # Quote all args as a single string, call |
|
94 | 94 | ESC_PAREN = '/' # Call first argument with rest of line as arguments |
|
95 | 95 | |
|
96 | 96 | #----------------------------------------------------------------------------- |
|
97 | 97 | # Utilities |
|
98 | 98 | #----------------------------------------------------------------------------- |
|
99 | 99 | |
|
100 | 100 | # FIXME: These are general-purpose utilities that later can be moved to the |
|
101 | 101 | # general ward. Kept here for now because we're being very strict about test |
|
102 | 102 | # coverage with this code, and this lets us ensure that we keep 100% coverage |
|
103 | 103 | # while developing. |
|
104 | 104 | |
|
105 | 105 | # compiled regexps for autoindent management |
|
106 | 106 | dedent_re = re.compile('|'.join([ |
|
107 | 107 | r'^\s+raise(\s.*)?$', # raise statement (+ space + other stuff, maybe) |
|
108 | 108 | r'^\s+raise\([^\)]*\).*$', # wacky raise with immediate open paren |
|
109 | 109 | r'^\s+return(\s.*)?$', # normal return (+ space + other stuff, maybe) |
|
110 | 110 | r'^\s+return\([^\)]*\).*$', # wacky return with immediate open paren |
|
111 | 111 | r'^\s+pass\s*$' # pass (optionally followed by trailing spaces) |
|
112 | 112 | ])) |
|
113 | 113 | ini_spaces_re = re.compile(r'^([ \t\r\f\v]+)') |
|
114 | 114 | |
|
115 | 115 | # regexp to match pure comment lines so we don't accidentally insert 'if 1:' |
|
116 | 116 | # before pure comments |
|
117 | 117 | comment_line_re = re.compile('^\s*\#') |
|
118 | 118 | |
|
119 | 119 | |
|
120 | 120 | def num_ini_spaces(s): |
|
121 | 121 | """Return the number of initial spaces in a string. |
|
122 | 122 | |
|
123 | 123 | Note that tabs are counted as a single space. For now, we do *not* support |
|
124 | 124 | mixing of tabs and spaces in the user's input. |
|
125 | 125 | |
|
126 | 126 | Parameters |
|
127 | 127 | ---------- |
|
128 | 128 | s : string |
|
129 | 129 | |
|
130 | 130 | Returns |
|
131 | 131 | ------- |
|
132 | 132 | n : int |
|
133 | 133 | """ |
|
134 | 134 | |
|
135 | 135 | ini_spaces = ini_spaces_re.match(s) |
|
136 | 136 | if ini_spaces: |
|
137 | 137 | return ini_spaces.end() |
|
138 | 138 | else: |
|
139 | 139 | return 0 |
|
140 | 140 | |
|
141 | 141 | |
|
142 | 142 | def remove_comments(src): |
|
143 | 143 | """Remove all comments from input source. |
|
144 | 144 | |
|
145 | 145 | Note: comments are NOT recognized inside of strings! |
|
146 | 146 | |
|
147 | 147 | Parameters |
|
148 | 148 | ---------- |
|
149 | 149 | src : string |
|
150 | 150 | A single or multiline input string. |
|
151 | 151 | |
|
152 | 152 | Returns |
|
153 | 153 | ------- |
|
154 | 154 | String with all Python comments removed. |
|
155 | 155 | """ |
|
156 | 156 | |
|
157 | 157 | return re.sub('#.*', '', src) |
|
158 | 158 | |
|
159 | 159 | |
|
160 | 160 | def get_input_encoding(): |
|
161 | 161 | """Return the default standard input encoding. |
|
162 | 162 | |
|
163 | 163 | If sys.stdin has no encoding, 'ascii' is returned.""" |
|
164 | 164 | # There are strange environments for which sys.stdin.encoding is None. We |
|
165 | 165 | # ensure that a valid encoding is returned. |
|
166 | 166 | encoding = getattr(sys.stdin, 'encoding', None) |
|
167 | 167 | if encoding is None: |
|
168 | 168 | encoding = 'ascii' |
|
169 | 169 | return encoding |
|
170 | 170 | |
|
171 | 171 | #----------------------------------------------------------------------------- |
|
172 | 172 | # Classes and functions for normal Python syntax handling |
|
173 | 173 | #----------------------------------------------------------------------------- |
|
174 | 174 | |
|
175 | 175 | class InputSplitter(object): |
|
176 | 176 | """An object that can accumulate lines of Python source before execution. |
|
177 | 177 | |
|
178 | 178 | This object is designed to be fed python source line-by-line, using |
|
179 | 179 | :meth:`push`. It will return on each push whether the currently pushed |
|
180 | 180 | code could be executed already. In addition, it provides a method called |
|
181 | 181 | :meth:`push_accepts_more` that can be used to query whether more input |
|
182 | 182 | can be pushed into a single interactive block. |
|
183 | 183 | |
|
184 | 184 | This is a simple example of how an interactive terminal-based client can use |
|
185 | 185 | this tool:: |
|
186 | 186 | |
|
187 | 187 | isp = InputSplitter() |
|
188 | 188 | while isp.push_accepts_more(): |
|
189 | 189 | indent = ' '*isp.indent_spaces |
|
190 | 190 | prompt = '>>> ' + indent |
|
191 | 191 | line = indent + raw_input(prompt) |
|
192 | 192 | isp.push(line) |
|
193 | 193 | print 'Input source was:\n', isp.source_reset(), |
|
194 | 194 | """ |
|
195 | 195 | # Number of spaces of indentation computed from input that has been pushed |
|
196 | 196 | # so far. This is the attributes callers should query to get the current |
|
197 | 197 | # indentation level, in order to provide auto-indent facilities. |
|
198 | 198 | indent_spaces = 0 |
|
199 | 199 | # String, indicating the default input encoding. It is computed by default |
|
200 | 200 | # at initialization time via get_input_encoding(), but it can be reset by a |
|
201 | 201 | # client with specific knowledge of the encoding. |
|
202 | 202 | encoding = '' |
|
203 | 203 | # String where the current full source input is stored, properly encoded. |
|
204 | 204 | # Reading this attribute is the normal way of querying the currently pushed |
|
205 | 205 | # source code, that has been properly encoded. |
|
206 | 206 | source = '' |
|
207 | 207 | # Code object corresponding to the current source. It is automatically |
|
208 | 208 | # synced to the source, so it can be queried at any time to obtain the code |
|
209 | 209 | # object; it will be None if the source doesn't compile to valid Python. |
|
210 | 210 | code = None |
|
211 | 211 | # Input mode |
|
212 | 212 | input_mode = 'line' |
|
213 | 213 | |
|
214 | 214 | # Private attributes |
|
215 | 215 | |
|
216 | 216 | # List with lines of input accumulated so far |
|
217 | 217 | _buffer = None |
|
218 | 218 | # Command compiler |
|
219 | 219 | _compile = None |
|
220 | 220 | # Mark when input has changed indentation all the way back to flush-left |
|
221 | 221 | _full_dedent = False |
|
222 | 222 | # Boolean indicating whether the current block is complete |
|
223 | 223 | _is_complete = None |
|
224 | 224 | |
|
225 | 225 | def __init__(self, input_mode=None): |
|
226 | 226 | """Create a new InputSplitter instance. |
|
227 | 227 | |
|
228 | 228 | Parameters |
|
229 | 229 | ---------- |
|
230 | 230 | input_mode : str |
|
231 | 231 | |
|
232 | 232 | One of ['line', 'cell']; default is 'line'. |
|
233 | 233 | |
|
234 | 234 | The input_mode parameter controls how new inputs are used when fed via |
|
235 | 235 | the :meth:`push` method: |
|
236 | 236 | |
|
237 | 237 | - 'line': meant for line-oriented clients, inputs are appended one at a |
|
238 | 238 | time to the internal buffer and the whole buffer is compiled. |
|
239 | 239 | |
|
240 | 240 | - 'cell': meant for clients that can edit multi-line 'cells' of text at |
|
241 | 241 | a time. A cell can contain one or more blocks that can be compile in |
|
242 | 242 | 'single' mode by Python. In this mode, each new input new input |
|
243 | 243 | completely replaces all prior inputs. Cell mode is thus equivalent |
|
244 | 244 | to prepending a full reset() to every push() call. |
|
245 | 245 | """ |
|
246 | 246 | self._buffer = [] |
|
247 | 247 | self._compile = codeop.CommandCompiler() |
|
248 | 248 | self.encoding = get_input_encoding() |
|
249 | 249 | self.input_mode = InputSplitter.input_mode if input_mode is None \ |
|
250 | 250 | else input_mode |
|
251 | 251 | |
|
252 | 252 | def reset(self): |
|
253 | 253 | """Reset the input buffer and associated state.""" |
|
254 | 254 | self.indent_spaces = 0 |
|
255 | 255 | self._buffer[:] = [] |
|
256 | 256 | self.source = '' |
|
257 | 257 | self.code = None |
|
258 | 258 | self._is_complete = False |
|
259 | 259 | self._full_dedent = False |
|
260 | 260 | |
|
261 | 261 | def source_reset(self): |
|
262 | 262 | """Return the input source and perform a full reset. |
|
263 | 263 | """ |
|
264 | 264 | out = self.source |
|
265 | 265 | self.reset() |
|
266 | 266 | return out |
|
267 | 267 | |
|
268 | 268 | def push(self, lines): |
|
269 | 269 | """Push one or more lines of input. |
|
270 | 270 | |
|
271 | 271 | This stores the given lines and returns a status code indicating |
|
272 | 272 | whether the code forms a complete Python block or not. |
|
273 | 273 | |
|
274 | 274 | Any exceptions generated in compilation are swallowed, but if an |
|
275 | 275 | exception was produced, the method returns True. |
|
276 | 276 | |
|
277 | 277 | Parameters |
|
278 | 278 | ---------- |
|
279 | 279 | lines : string |
|
280 | 280 | One or more lines of Python input. |
|
281 | 281 | |
|
282 | 282 | Returns |
|
283 | 283 | ------- |
|
284 | 284 | is_complete : boolean |
|
285 | 285 | True if the current input source (the result of the current input |
|
286 | 286 | plus prior inputs) forms a complete Python execution block. Note that |
|
287 | 287 | this value is also stored as a private attribute (_is_complete), so it |
|
288 | 288 | can be queried at any time. |
|
289 | 289 | """ |
|
290 | 290 | if self.input_mode == 'cell': |
|
291 | 291 | self.reset() |
|
292 | 292 | |
|
293 | 293 | self._store(lines) |
|
294 | 294 | source = self.source |
|
295 | 295 | |
|
296 | 296 | # Before calling _compile(), reset the code object to None so that if an |
|
297 | 297 | # exception is raised in compilation, we don't mislead by having |
|
298 | 298 | # inconsistent code/source attributes. |
|
299 | 299 | self.code, self._is_complete = None, None |
|
300 | 300 | |
|
301 | 301 | # Honor termination lines properly |
|
302 | 302 | if source.rstrip().endswith('\\'): |
|
303 | 303 | return False |
|
304 | 304 | |
|
305 | 305 | self._update_indent(lines) |
|
306 | 306 | try: |
|
307 | 307 | self.code = self._compile(source, symbol="exec") |
|
308 | 308 | # Invalid syntax can produce any of a number of different errors from |
|
309 | 309 | # inside the compiler, so we have to catch them all. Syntax errors |
|
310 | 310 | # immediately produce a 'ready' block, so the invalid Python can be |
|
311 | 311 | # sent to the kernel for evaluation with possible ipython |
|
312 | 312 | # special-syntax conversion. |
|
313 | 313 | except (SyntaxError, OverflowError, ValueError, TypeError, |
|
314 | 314 | MemoryError): |
|
315 | 315 | self._is_complete = True |
|
316 | 316 | else: |
|
317 | 317 | # Compilation didn't produce any exceptions (though it may not have |
|
318 | 318 | # given a complete code object) |
|
319 | 319 | self._is_complete = self.code is not None |
|
320 | 320 | |
|
321 | 321 | return self._is_complete |
|
322 | 322 | |
|
323 | 323 | def push_accepts_more(self): |
|
324 | 324 | """Return whether a block of interactive input can accept more input. |
|
325 | 325 | |
|
326 | 326 | This method is meant to be used by line-oriented frontends, who need to |
|
327 | 327 | guess whether a block is complete or not based solely on prior and |
|
328 | 328 | current input lines. The InputSplitter considers it has a complete |
|
329 | 329 | interactive block and will not accept more input only when either a |
|
330 | 330 | SyntaxError is raised, or *all* of the following are true: |
|
331 | 331 | |
|
332 | 332 | 1. The input compiles to a complete statement. |
|
333 | 333 | |
|
334 | 334 | 2. The indentation level is flush-left (because if we are indented, |
|
335 | 335 | like inside a function definition or for loop, we need to keep |
|
336 | 336 | reading new input). |
|
337 | 337 | |
|
338 | 338 | 3. There is one extra line consisting only of whitespace. |
|
339 | 339 | |
|
340 | 340 | Because of condition #3, this method should be used only by |
|
341 | 341 | *line-oriented* frontends, since it means that intermediate blank lines |
|
342 | 342 | are not allowed in function definitions (or any other indented block). |
|
343 | 343 | |
|
344 | 344 | Block-oriented frontends that have a separate keyboard event to |
|
345 | 345 | indicate execution should use the :meth:`split_blocks` method instead. |
|
346 | 346 | |
|
347 | 347 | If the current input produces a syntax error, this method immediately |
|
348 | 348 | returns False but does *not* raise the syntax error exception, as |
|
349 | 349 | typically clients will want to send invalid syntax to an execution |
|
350 | 350 | backend which might convert the invalid syntax into valid Python via |
|
351 | 351 | one of the dynamic IPython mechanisms. |
|
352 | 352 | """ |
|
353 | 353 | |
|
354 | 354 | # With incomplete input, unconditionally accept more |
|
355 | 355 | if not self._is_complete: |
|
356 | 356 | return True |
|
357 | 357 | |
|
358 | 358 | # If we already have complete input and we're flush left, the answer |
|
359 | 359 | # depends. In line mode, if there hasn't been any indentation, |
|
360 | 360 | # that's it. If we've come back from some indentation, we need |
|
361 | 361 | # the blank final line to finish. |
|
362 | 362 | # In cell mode, we need to check how many blocks the input so far |
|
363 | 363 | # compiles into, because if there's already more than one full |
|
364 | 364 | # independent block of input, then the client has entered full |
|
365 | 365 | # 'cell' mode and is feeding lines that each is complete. In this |
|
366 | 366 | # case we should then keep accepting. The Qt terminal-like console |
|
367 | 367 | # does precisely this, to provide the convenience of terminal-like |
|
368 | 368 | # input of single expressions, but allowing the user (with a |
|
369 | 369 | # separate keystroke) to switch to 'cell' mode and type multiple |
|
370 | 370 | # expressions in one shot. |
|
371 | 371 | if self.indent_spaces==0: |
|
372 | 372 | if self.input_mode=='line': |
|
373 | 373 | if not self._full_dedent: |
|
374 | 374 | return False |
|
375 | 375 | else: |
|
376 | 376 | try: |
|
377 | 377 | code_ast = ast.parse(u''.join(self._buffer)) |
|
378 | 378 | except Exception: |
|
379 | 379 | return False |
|
380 | 380 | else: |
|
381 | 381 | if len(code_ast.body) == 1: |
|
382 | 382 | return False |
|
383 | 383 | |
|
384 | 384 | # When input is complete, then termination is marked by an extra blank |
|
385 | 385 | # line at the end. |
|
386 | 386 | last_line = self.source.splitlines()[-1] |
|
387 | 387 | return bool(last_line and not last_line.isspace()) |
|
388 | 388 | |
|
389 | 389 | #------------------------------------------------------------------------ |
|
390 | 390 | # Private interface |
|
391 | 391 | #------------------------------------------------------------------------ |
|
392 | 392 | |
|
393 | 393 | def _find_indent(self, line): |
|
394 | 394 | """Compute the new indentation level for a single line. |
|
395 | 395 | |
|
396 | 396 | Parameters |
|
397 | 397 | ---------- |
|
398 | 398 | line : str |
|
399 | 399 | A single new line of non-whitespace, non-comment Python input. |
|
400 | 400 | |
|
401 | 401 | Returns |
|
402 | 402 | ------- |
|
403 | 403 | indent_spaces : int |
|
404 | 404 | New value for the indent level (it may be equal to self.indent_spaces |
|
405 | 405 | if indentation doesn't change. |
|
406 | 406 | |
|
407 | 407 | full_dedent : boolean |
|
408 | 408 | Whether the new line causes a full flush-left dedent. |
|
409 | 409 | """ |
|
410 | 410 | indent_spaces = self.indent_spaces |
|
411 | 411 | full_dedent = self._full_dedent |
|
412 | 412 | |
|
413 | 413 | inisp = num_ini_spaces(line) |
|
414 | 414 | if inisp < indent_spaces: |
|
415 | 415 | indent_spaces = inisp |
|
416 | 416 | if indent_spaces <= 0: |
|
417 | 417 | #print 'Full dedent in text',self.source # dbg |
|
418 | 418 | full_dedent = True |
|
419 | 419 | |
|
420 | 420 | if line[-1] == ':': |
|
421 | 421 | indent_spaces += 4 |
|
422 | 422 | elif dedent_re.match(line): |
|
423 | 423 | indent_spaces -= 4 |
|
424 | 424 | if indent_spaces <= 0: |
|
425 | 425 | full_dedent = True |
|
426 | 426 | |
|
427 | 427 | # Safety |
|
428 | 428 | if indent_spaces < 0: |
|
429 | 429 | indent_spaces = 0 |
|
430 | 430 | #print 'safety' # dbg |
|
431 | 431 | |
|
432 | 432 | return indent_spaces, full_dedent |
|
433 | 433 | |
|
434 | 434 | def _update_indent(self, lines): |
|
435 | 435 | for line in remove_comments(lines).splitlines(): |
|
436 | 436 | if line and not line.isspace(): |
|
437 | 437 | self.indent_spaces, self._full_dedent = self._find_indent(line) |
|
438 | 438 | |
|
439 | 439 | def _store(self, lines, buffer=None, store='source'): |
|
440 | 440 | """Store one or more lines of input. |
|
441 | 441 | |
|
442 | 442 | If input lines are not newline-terminated, a newline is automatically |
|
443 | 443 | appended.""" |
|
444 | 444 | |
|
445 | 445 | if buffer is None: |
|
446 | 446 | buffer = self._buffer |
|
447 | 447 | |
|
448 | 448 | if lines.endswith('\n'): |
|
449 | 449 | buffer.append(lines) |
|
450 | 450 | else: |
|
451 | 451 | buffer.append(lines+'\n') |
|
452 | 452 | setattr(self, store, self._set_source(buffer)) |
|
453 | 453 | |
|
454 | 454 | def _set_source(self, buffer): |
|
455 | 455 | return u''.join(buffer) |
|
456 | 456 | |
|
457 | 457 | |
|
458 | 458 | #----------------------------------------------------------------------------- |
|
459 | 459 | # Functions and classes for IPython-specific syntactic support |
|
460 | 460 | #----------------------------------------------------------------------------- |
|
461 | 461 | |
|
462 | 462 | # RegExp for splitting line contents into pre-char//first word-method//rest. |
|
463 | 463 | # For clarity, each group in on one line. |
|
464 | 464 | |
|
465 | 465 | line_split = re.compile(""" |
|
466 | 466 | ^(\s*) # any leading space |
|
467 | 467 | ([,;/%]|!!?|\?\??) # escape character or characters |
|
468 | 468 | \s*(%?[\w\.\*]*) # function/method, possibly with leading % |
|
469 | 469 | # to correctly treat things like '?%magic' |
|
470 | 470 | (\s+.*$|$) # rest of line |
|
471 | 471 | """, re.VERBOSE) |
|
472 | 472 | |
|
473 | 473 | |
|
474 | 474 | def split_user_input(line): |
|
475 | 475 | """Split user input into early whitespace, esc-char, function part and rest. |
|
476 | 476 | |
|
477 | 477 | This is currently handles lines with '=' in them in a very inconsistent |
|
478 | 478 | manner. |
|
479 | 479 | |
|
480 | 480 | Examples |
|
481 | 481 | ======== |
|
482 | 482 | >>> split_user_input('x=1') |
|
483 | 483 | ('', '', 'x=1', '') |
|
484 | 484 | >>> split_user_input('?') |
|
485 | 485 | ('', '?', '', '') |
|
486 | 486 | >>> split_user_input('??') |
|
487 | 487 | ('', '??', '', '') |
|
488 | 488 | >>> split_user_input(' ?') |
|
489 | 489 | (' ', '?', '', '') |
|
490 | 490 | >>> split_user_input(' ??') |
|
491 | 491 | (' ', '??', '', '') |
|
492 | 492 | >>> split_user_input('??x') |
|
493 | 493 | ('', '??', 'x', '') |
|
494 | 494 | >>> split_user_input('?x=1') |
|
495 | 495 | ('', '', '?x=1', '') |
|
496 | 496 | >>> split_user_input('!ls') |
|
497 | 497 | ('', '!', 'ls', '') |
|
498 | 498 | >>> split_user_input(' !ls') |
|
499 | 499 | (' ', '!', 'ls', '') |
|
500 | 500 | >>> split_user_input('!!ls') |
|
501 | 501 | ('', '!!', 'ls', '') |
|
502 | 502 | >>> split_user_input(' !!ls') |
|
503 | 503 | (' ', '!!', 'ls', '') |
|
504 | 504 | >>> split_user_input(',ls') |
|
505 | 505 | ('', ',', 'ls', '') |
|
506 | 506 | >>> split_user_input(';ls') |
|
507 | 507 | ('', ';', 'ls', '') |
|
508 | 508 | >>> split_user_input(' ;ls') |
|
509 | 509 | (' ', ';', 'ls', '') |
|
510 | 510 | >>> split_user_input('f.g(x)') |
|
511 | 511 | ('', '', 'f.g(x)', '') |
|
512 | 512 | >>> split_user_input('f.g (x)') |
|
513 | 513 | ('', '', 'f.g', '(x)') |
|
514 | 514 | >>> split_user_input('?%hist') |
|
515 | 515 | ('', '?', '%hist', '') |
|
516 | 516 | >>> split_user_input('?x*') |
|
517 | 517 | ('', '?', 'x*', '') |
|
518 | 518 | """ |
|
519 | 519 | match = line_split.match(line) |
|
520 | 520 | if match: |
|
521 | 521 | lspace, esc, fpart, rest = match.groups() |
|
522 | 522 | else: |
|
523 | 523 | # print "match failed for line '%s'" % line |
|
524 | 524 | try: |
|
525 | 525 | fpart, rest = line.split(None, 1) |
|
526 | 526 | except ValueError: |
|
527 | 527 | # print "split failed for line '%s'" % line |
|
528 | 528 | fpart, rest = line,'' |
|
529 | 529 | lspace = re.match('^(\s*)(.*)', line).groups()[0] |
|
530 | 530 | esc = '' |
|
531 | 531 | |
|
532 | 532 | # fpart has to be a valid python identifier, so it better be only pure |
|
533 | 533 | # ascii, no unicode: |
|
534 | 534 | try: |
|
535 | 535 | fpart = fpart.encode('ascii') |
|
536 | 536 | except UnicodeEncodeError: |
|
537 | 537 | lspace = unicode(lspace) |
|
538 | 538 | rest = fpart + u' ' + rest |
|
539 | 539 | fpart = u'' |
|
540 | 540 | |
|
541 | 541 | #print 'line:<%s>' % line # dbg |
|
542 | 542 | #print 'esc <%s> fpart <%s> rest <%s>' % (esc,fpart.strip(),rest) # dbg |
|
543 | 543 | return lspace, esc, fpart.strip(), rest.lstrip() |
|
544 | 544 | |
|
545 | 545 | |
|
546 | 546 | # The escaped translators ALL receive a line where their own escape has been |
|
547 | 547 | # stripped. Only '?' is valid at the end of the line, all others can only be |
|
548 | 548 | # placed at the start. |
|
549 | 549 | |
|
550 | 550 | class LineInfo(object): |
|
551 | 551 | """A single line of input and associated info. |
|
552 | 552 | |
|
553 | 553 | This is a utility class that mostly wraps the output of |
|
554 | 554 | :func:`split_user_input` into a convenient object to be passed around |
|
555 | 555 | during input transformations. |
|
556 | 556 | |
|
557 | 557 | Includes the following as properties: |
|
558 | 558 | |
|
559 | 559 | line |
|
560 | 560 | The original, raw line |
|
561 | 561 | |
|
562 | 562 | lspace |
|
563 | 563 | Any early whitespace before actual text starts. |
|
564 | 564 | |
|
565 | 565 | esc |
|
566 | 566 | The initial esc character (or characters, for double-char escapes like |
|
567 | 567 | '??' or '!!'). |
|
568 | 568 | |
|
569 | 569 | fpart |
|
570 | 570 | The 'function part', which is basically the maximal initial sequence |
|
571 | 571 | of valid python identifiers and the '.' character. This is what is |
|
572 | 572 | checked for alias and magic transformations, used for auto-calling, |
|
573 | 573 | etc. |
|
574 | 574 | |
|
575 | 575 | rest |
|
576 | 576 | Everything else on the line. |
|
577 | 577 | """ |
|
578 | 578 | def __init__(self, line): |
|
579 | 579 | self.line = line |
|
580 | 580 | self.lspace, self.esc, self.fpart, self.rest = \ |
|
581 | 581 | split_user_input(line) |
|
582 | 582 | |
|
583 | 583 | def __str__(self): |
|
584 | 584 | return "LineInfo [%s|%s|%s|%s]" % (self.lspace, self.esc, |
|
585 | 585 | self.fpart, self.rest) |
|
586 | 586 | |
|
587 | 587 | |
|
588 | 588 | # Transformations of the special syntaxes that don't rely on an explicit escape |
|
589 | 589 | # character but instead on patterns on the input line |
|
590 | 590 | |
|
591 | 591 | # The core transformations are implemented as standalone functions that can be |
|
592 | 592 | # tested and validated in isolation. Each of these uses a regexp, we |
|
593 | 593 | # pre-compile these and keep them close to each function definition for clarity |
|
594 | 594 | |
|
595 | 595 | _assign_system_re = re.compile(r'(?P<lhs>(\s*)([\w\.]+)((\s*,\s*[\w\.]+)*))' |
|
596 | 596 | r'\s*=\s*!\s*(?P<cmd>.*)') |
|
597 | 597 | |
|
598 | 598 | def transform_assign_system(line): |
|
599 | 599 | """Handle the `files = !ls` syntax.""" |
|
600 | 600 | m = _assign_system_re.match(line) |
|
601 | 601 | if m is not None: |
|
602 | 602 | cmd = m.group('cmd') |
|
603 | 603 | lhs = m.group('lhs') |
|
604 | 604 | expr = make_quoted_expr(cmd) |
|
605 | 605 | new_line = '%s = get_ipython().getoutput(%s)' % (lhs, expr) |
|
606 | 606 | return new_line |
|
607 | 607 | return line |
|
608 | 608 | |
|
609 | 609 | |
|
610 | 610 | _assign_magic_re = re.compile(r'(?P<lhs>(\s*)([\w\.]+)((\s*,\s*[\w\.]+)*))' |
|
611 | 611 | r'\s*=\s*%\s*(?P<cmd>.*)') |
|
612 | 612 | |
|
613 | 613 | def transform_assign_magic(line): |
|
614 | 614 | """Handle the `a = %who` syntax.""" |
|
615 | 615 | m = _assign_magic_re.match(line) |
|
616 | 616 | if m is not None: |
|
617 | 617 | cmd = m.group('cmd') |
|
618 | 618 | lhs = m.group('lhs') |
|
619 | 619 | expr = make_quoted_expr(cmd) |
|
620 | 620 | new_line = '%s = get_ipython().magic(%s)' % (lhs, expr) |
|
621 | 621 | return new_line |
|
622 | 622 | return line |
|
623 | 623 | |
|
624 | 624 | |
|
625 | 625 | _classic_prompt_re = re.compile(r'^([ \t]*>>> |^[ \t]*\.\.\. )') |
|
626 | 626 | |
|
627 | 627 | def transform_classic_prompt(line): |
|
628 | 628 | """Handle inputs that start with '>>> ' syntax.""" |
|
629 | 629 | |
|
630 | 630 | if not line or line.isspace(): |
|
631 | 631 | return line |
|
632 | 632 | m = _classic_prompt_re.match(line) |
|
633 | 633 | if m: |
|
634 | 634 | return line[len(m.group(0)):] |
|
635 | 635 | else: |
|
636 | 636 | return line |
|
637 | 637 | |
|
638 | 638 | |
|
639 | 639 | _ipy_prompt_re = re.compile(r'^([ \t]*In \[\d+\]: |^[ \t]*\ \ \ \.\.\.+: )') |
|
640 | 640 | |
|
641 | 641 | def transform_ipy_prompt(line): |
|
642 | 642 | """Handle inputs that start classic IPython prompt syntax.""" |
|
643 | 643 | |
|
644 | 644 | if not line or line.isspace(): |
|
645 | 645 | return line |
|
646 | 646 | #print 'LINE: %r' % line # dbg |
|
647 | 647 | m = _ipy_prompt_re.match(line) |
|
648 | 648 | if m: |
|
649 | 649 | #print 'MATCH! %r -> %r' % (line, line[len(m.group(0)):]) # dbg |
|
650 | 650 | return line[len(m.group(0)):] |
|
651 | 651 | else: |
|
652 | 652 | return line |
|
653 | 653 | |
|
654 | 654 | |
|
655 | 655 | def _make_help_call(target, esc, lspace): |
|
656 | 656 | """Prepares a pinfo(2)/psearch call from a target name and the escape |
|
657 | 657 | (i.e. ? or ??)""" |
|
658 | 658 | method = 'pinfo2' if esc == '??' \ |
|
659 | 659 | else 'psearch' if '*' in target \ |
|
660 | 660 | else 'pinfo' |
|
661 | 661 | |
|
662 | 662 | tpl = '%sget_ipython().magic(u"%s %s")' |
|
663 | 663 | return tpl % (lspace, method, target) |
|
664 | 664 | |
|
665 | 665 | _initial_space_re = re.compile(r'\s*') |
|
666 | 666 | _help_end_re = re.compile(r"""(%? |
|
667 | 667 | [a-zA-Z_*][a-zA-Z0-9_*]* # Variable name |
|
668 | (.[a-zA-Z_*][a-zA-Z0-9_*]*)* # .etc.etc | |
|
668 | (\.[a-zA-Z_*][a-zA-Z0-9_*]*)* # .etc.etc | |
|
669 | 669 | ) |
|
670 | 670 | (\?\??)$ # ? or ??""", |
|
671 | 671 | re.VERBOSE) |
|
672 | 672 | def transform_help_end(line): |
|
673 | 673 | """Translate lines with ?/?? at the end""" |
|
674 | 674 | m = _help_end_re.search(line) |
|
675 | 675 | if m is None: |
|
676 | 676 | return line |
|
677 | 677 | target = m.group(1) |
|
678 | 678 | esc = m.group(3) |
|
679 | 679 | lspace = _initial_space_re.match(line).group(0) |
|
680 | 680 | return _make_help_call(target, esc, lspace) |
|
681 | 681 | |
|
682 | 682 | |
|
683 | 683 | class EscapedTransformer(object): |
|
684 | 684 | """Class to transform lines that are explicitly escaped out.""" |
|
685 | 685 | |
|
686 | 686 | def __init__(self): |
|
687 | 687 | tr = { ESC_SHELL : self._tr_system, |
|
688 | 688 | ESC_SH_CAP : self._tr_system2, |
|
689 | 689 | ESC_HELP : self._tr_help, |
|
690 | 690 | ESC_HELP2 : self._tr_help, |
|
691 | 691 | ESC_MAGIC : self._tr_magic, |
|
692 | 692 | ESC_QUOTE : self._tr_quote, |
|
693 | 693 | ESC_QUOTE2 : self._tr_quote2, |
|
694 | 694 | ESC_PAREN : self._tr_paren } |
|
695 | 695 | self.tr = tr |
|
696 | 696 | |
|
697 | 697 | # Support for syntax transformations that use explicit escapes typed by the |
|
698 | 698 | # user at the beginning of a line |
|
699 | 699 | @staticmethod |
|
700 | 700 | def _tr_system(line_info): |
|
701 | 701 | "Translate lines escaped with: !" |
|
702 | 702 | cmd = line_info.line.lstrip().lstrip(ESC_SHELL) |
|
703 | 703 | return '%sget_ipython().system(%s)' % (line_info.lspace, |
|
704 | 704 | make_quoted_expr(cmd)) |
|
705 | 705 | |
|
706 | 706 | @staticmethod |
|
707 | 707 | def _tr_system2(line_info): |
|
708 | 708 | "Translate lines escaped with: !!" |
|
709 | 709 | cmd = line_info.line.lstrip()[2:] |
|
710 | 710 | return '%sget_ipython().getoutput(%s)' % (line_info.lspace, |
|
711 | 711 | make_quoted_expr(cmd)) |
|
712 | 712 | |
|
713 | 713 | @staticmethod |
|
714 | 714 | def _tr_help(line_info): |
|
715 | 715 | "Translate lines escaped with: ?/??" |
|
716 | 716 | # A naked help line should just fire the intro help screen |
|
717 | 717 | if not line_info.line[1:]: |
|
718 | 718 | return 'get_ipython().show_usage()' |
|
719 | 719 | |
|
720 | 720 | return _make_help_call(line_info.fpart, line_info.esc, line_info.lspace) |
|
721 | 721 | |
|
722 | 722 | @staticmethod |
|
723 | 723 | def _tr_magic(line_info): |
|
724 | 724 | "Translate lines escaped with: %" |
|
725 | 725 | tpl = '%sget_ipython().magic(%s)' |
|
726 | 726 | cmd = make_quoted_expr(' '.join([line_info.fpart, |
|
727 | 727 | line_info.rest]).strip()) |
|
728 | 728 | return tpl % (line_info.lspace, cmd) |
|
729 | 729 | |
|
730 | 730 | @staticmethod |
|
731 | 731 | def _tr_quote(line_info): |
|
732 | 732 | "Translate lines escaped with: ," |
|
733 | 733 | return '%s%s("%s")' % (line_info.lspace, line_info.fpart, |
|
734 | 734 | '", "'.join(line_info.rest.split()) ) |
|
735 | 735 | |
|
736 | 736 | @staticmethod |
|
737 | 737 | def _tr_quote2(line_info): |
|
738 | 738 | "Translate lines escaped with: ;" |
|
739 | 739 | return '%s%s("%s")' % (line_info.lspace, line_info.fpart, |
|
740 | 740 | line_info.rest) |
|
741 | 741 | |
|
742 | 742 | @staticmethod |
|
743 | 743 | def _tr_paren(line_info): |
|
744 | 744 | "Translate lines escaped with: /" |
|
745 | 745 | return '%s%s(%s)' % (line_info.lspace, line_info.fpart, |
|
746 | 746 | ", ".join(line_info.rest.split())) |
|
747 | 747 | |
|
748 | 748 | def __call__(self, line): |
|
749 | 749 | """Class to transform lines that are explicitly escaped out. |
|
750 | 750 | |
|
751 | 751 | This calls the above _tr_* static methods for the actual line |
|
752 | 752 | translations.""" |
|
753 | 753 | |
|
754 | 754 | # Empty lines just get returned unmodified |
|
755 | 755 | if not line or line.isspace(): |
|
756 | 756 | return line |
|
757 | 757 | |
|
758 | 758 | # Get line endpoints, where the escapes can be |
|
759 | 759 | line_info = LineInfo(line) |
|
760 | 760 | |
|
761 | 761 | if not line_info.esc in self.tr: |
|
762 | 762 | # If we don't recognize the escape, don't modify the line |
|
763 | 763 | return line |
|
764 | 764 | |
|
765 | 765 | return self.tr[line_info.esc](line_info) |
|
766 | 766 | |
|
767 | 767 | |
|
768 | 768 | # A function-looking object to be used by the rest of the code. The purpose of |
|
769 | 769 | # the class in this case is to organize related functionality, more than to |
|
770 | 770 | # manage state. |
|
771 | 771 | transform_escaped = EscapedTransformer() |
|
772 | 772 | |
|
773 | 773 | |
|
774 | 774 | class IPythonInputSplitter(InputSplitter): |
|
775 | 775 | """An input splitter that recognizes all of IPython's special syntax.""" |
|
776 | 776 | |
|
777 | 777 | # String with raw, untransformed input. |
|
778 | 778 | source_raw = '' |
|
779 | 779 | |
|
780 | 780 | # Private attributes |
|
781 | 781 | |
|
782 | 782 | # List with lines of raw input accumulated so far. |
|
783 | 783 | _buffer_raw = None |
|
784 | 784 | |
|
785 | 785 | def __init__(self, input_mode=None): |
|
786 | 786 | InputSplitter.__init__(self, input_mode) |
|
787 | 787 | self._buffer_raw = [] |
|
788 | 788 | |
|
789 | 789 | def reset(self): |
|
790 | 790 | """Reset the input buffer and associated state.""" |
|
791 | 791 | InputSplitter.reset(self) |
|
792 | 792 | self._buffer_raw[:] = [] |
|
793 | 793 | self.source_raw = '' |
|
794 | 794 | |
|
795 | 795 | def source_raw_reset(self): |
|
796 | 796 | """Return input and raw source and perform a full reset. |
|
797 | 797 | """ |
|
798 | 798 | out = self.source |
|
799 | 799 | out_r = self.source_raw |
|
800 | 800 | self.reset() |
|
801 | 801 | return out, out_r |
|
802 | 802 | |
|
803 | 803 | def push(self, lines): |
|
804 | 804 | """Push one or more lines of IPython input. |
|
805 | 805 | """ |
|
806 | 806 | if not lines: |
|
807 | 807 | return super(IPythonInputSplitter, self).push(lines) |
|
808 | 808 | |
|
809 | 809 | # We must ensure all input is pure unicode |
|
810 | 810 | if type(lines)==str: |
|
811 | 811 | lines = lines.decode(self.encoding) |
|
812 | 812 | |
|
813 | 813 | lines_list = lines.splitlines() |
|
814 | 814 | |
|
815 |
transforms = [transform_ |
|
|
816 |
transform_ |
|
|
817 |
transform_ |
|
|
815 | transforms = [transform_ipy_prompt, transform_classic_prompt, | |
|
816 | transform_escaped, transform_help_end, | |
|
817 | transform_assign_system, transform_assign_magic] | |
|
818 | 818 | |
|
819 | 819 | # Transform logic |
|
820 | 820 | # |
|
821 | 821 | # We only apply the line transformers to the input if we have either no |
|
822 | 822 | # input yet, or complete input, or if the last line of the buffer ends |
|
823 | 823 | # with ':' (opening an indented block). This prevents the accidental |
|
824 | 824 | # transformation of escapes inside multiline expressions like |
|
825 | 825 | # triple-quoted strings or parenthesized expressions. |
|
826 | 826 | # |
|
827 | 827 | # The last heuristic, while ugly, ensures that the first line of an |
|
828 | 828 | # indented block is correctly transformed. |
|
829 | 829 | # |
|
830 | 830 | # FIXME: try to find a cleaner approach for this last bit. |
|
831 | 831 | |
|
832 | 832 | # If we were in 'block' mode, since we're going to pump the parent |
|
833 | 833 | # class by hand line by line, we need to temporarily switch out to |
|
834 | 834 | # 'line' mode, do a single manual reset and then feed the lines one |
|
835 | 835 | # by one. Note that this only matters if the input has more than one |
|
836 | 836 | # line. |
|
837 | 837 | changed_input_mode = False |
|
838 | 838 | |
|
839 | 839 | if self.input_mode == 'cell': |
|
840 | 840 | self.reset() |
|
841 | 841 | changed_input_mode = True |
|
842 | 842 | saved_input_mode = 'cell' |
|
843 | 843 | self.input_mode = 'line' |
|
844 | 844 | |
|
845 | 845 | # Store raw source before applying any transformations to it. Note |
|
846 | 846 | # that this must be done *after* the reset() call that would otherwise |
|
847 | 847 | # flush the buffer. |
|
848 | 848 | self._store(lines, self._buffer_raw, 'source_raw') |
|
849 | 849 | |
|
850 | 850 | try: |
|
851 | 851 | push = super(IPythonInputSplitter, self).push |
|
852 | 852 | for line in lines_list: |
|
853 | 853 | if self._is_complete or not self._buffer or \ |
|
854 | 854 | (self._buffer and self._buffer[-1].rstrip().endswith(':')): |
|
855 | 855 | for f in transforms: |
|
856 | 856 | line = f(line) |
|
857 | 857 | |
|
858 | 858 | out = push(line) |
|
859 | 859 | finally: |
|
860 | 860 | if changed_input_mode: |
|
861 | 861 | self.input_mode = saved_input_mode |
|
862 | 862 | return out |
@@ -1,664 +1,672 b'' | |||
|
1 | 1 | # -*- coding: utf-8 -*- |
|
2 | 2 | """Tests for the inputsplitter module. |
|
3 | 3 | |
|
4 | 4 | Authors |
|
5 | 5 | ------- |
|
6 | 6 | * Fernando Perez |
|
7 | 7 | * Robert Kern |
|
8 | 8 | """ |
|
9 | 9 | #----------------------------------------------------------------------------- |
|
10 | 10 | # Copyright (C) 2010 The IPython Development Team |
|
11 | 11 | # |
|
12 | 12 | # Distributed under the terms of the BSD License. The full license is in |
|
13 | 13 | # the file COPYING, distributed as part of this software. |
|
14 | 14 | #----------------------------------------------------------------------------- |
|
15 | 15 | |
|
16 | 16 | #----------------------------------------------------------------------------- |
|
17 | 17 | # Imports |
|
18 | 18 | #----------------------------------------------------------------------------- |
|
19 | 19 | # stdlib |
|
20 | 20 | import unittest |
|
21 | 21 | import sys |
|
22 | 22 | |
|
23 | 23 | # Third party |
|
24 | 24 | import nose.tools as nt |
|
25 | 25 | |
|
26 | 26 | # Our own |
|
27 | 27 | from IPython.core import inputsplitter as isp |
|
28 | 28 | |
|
29 | 29 | #----------------------------------------------------------------------------- |
|
30 | 30 | # Semi-complete examples (also used as tests) |
|
31 | 31 | #----------------------------------------------------------------------------- |
|
32 | 32 | |
|
33 | 33 | # Note: at the bottom, there's a slightly more complete version of this that |
|
34 | 34 | # can be useful during development of code here. |
|
35 | 35 | |
|
36 | 36 | def mini_interactive_loop(input_func): |
|
37 | 37 | """Minimal example of the logic of an interactive interpreter loop. |
|
38 | 38 | |
|
39 | 39 | This serves as an example, and it is used by the test system with a fake |
|
40 | 40 | raw_input that simulates interactive input.""" |
|
41 | 41 | |
|
42 | 42 | from IPython.core.inputsplitter import InputSplitter |
|
43 | 43 | |
|
44 | 44 | isp = InputSplitter() |
|
45 | 45 | # In practice, this input loop would be wrapped in an outside loop to read |
|
46 | 46 | # input indefinitely, until some exit/quit command was issued. Here we |
|
47 | 47 | # only illustrate the basic inner loop. |
|
48 | 48 | while isp.push_accepts_more(): |
|
49 | 49 | indent = ' '*isp.indent_spaces |
|
50 | 50 | prompt = '>>> ' + indent |
|
51 | 51 | line = indent + input_func(prompt) |
|
52 | 52 | isp.push(line) |
|
53 | 53 | |
|
54 | 54 | # Here we just return input so we can use it in a test suite, but a real |
|
55 | 55 | # interpreter would instead send it for execution somewhere. |
|
56 | 56 | src = isp.source_reset() |
|
57 | 57 | #print 'Input source was:\n', src # dbg |
|
58 | 58 | return src |
|
59 | 59 | |
|
60 | 60 | #----------------------------------------------------------------------------- |
|
61 | 61 | # Test utilities, just for local use |
|
62 | 62 | #----------------------------------------------------------------------------- |
|
63 | 63 | |
|
64 | 64 | def assemble(block): |
|
65 | 65 | """Assemble a block into multi-line sub-blocks.""" |
|
66 | 66 | return ['\n'.join(sub_block)+'\n' for sub_block in block] |
|
67 | 67 | |
|
68 | 68 | |
|
69 | 69 | def pseudo_input(lines): |
|
70 | 70 | """Return a function that acts like raw_input but feeds the input list.""" |
|
71 | 71 | ilines = iter(lines) |
|
72 | 72 | def raw_in(prompt): |
|
73 | 73 | try: |
|
74 | 74 | return next(ilines) |
|
75 | 75 | except StopIteration: |
|
76 | 76 | return '' |
|
77 | 77 | return raw_in |
|
78 | 78 | |
|
79 | 79 | #----------------------------------------------------------------------------- |
|
80 | 80 | # Tests |
|
81 | 81 | #----------------------------------------------------------------------------- |
|
82 | 82 | def test_spaces(): |
|
83 | 83 | tests = [('', 0), |
|
84 | 84 | (' ', 1), |
|
85 | 85 | ('\n', 0), |
|
86 | 86 | (' \n', 1), |
|
87 | 87 | ('x', 0), |
|
88 | 88 | (' x', 1), |
|
89 | 89 | (' x',2), |
|
90 | 90 | (' x',4), |
|
91 | 91 | # Note: tabs are counted as a single whitespace! |
|
92 | 92 | ('\tx', 1), |
|
93 | 93 | ('\t x', 2), |
|
94 | 94 | ] |
|
95 | 95 | |
|
96 | 96 | for s, nsp in tests: |
|
97 | 97 | nt.assert_equal(isp.num_ini_spaces(s), nsp) |
|
98 | 98 | |
|
99 | 99 | |
|
100 | 100 | def test_remove_comments(): |
|
101 | 101 | tests = [('text', 'text'), |
|
102 | 102 | ('text # comment', 'text '), |
|
103 | 103 | ('text # comment\n', 'text \n'), |
|
104 | 104 | ('text # comment \n', 'text \n'), |
|
105 | 105 | ('line # c \nline\n','line \nline\n'), |
|
106 | 106 | ('line # c \nline#c2 \nline\nline #c\n\n', |
|
107 | 107 | 'line \nline\nline\nline \n\n'), |
|
108 | 108 | ] |
|
109 | 109 | |
|
110 | 110 | for inp, out in tests: |
|
111 | 111 | nt.assert_equal(isp.remove_comments(inp), out) |
|
112 | 112 | |
|
113 | 113 | |
|
114 | 114 | def test_get_input_encoding(): |
|
115 | 115 | encoding = isp.get_input_encoding() |
|
116 | 116 | nt.assert_true(isinstance(encoding, basestring)) |
|
117 | 117 | # simple-minded check that at least encoding a simple string works with the |
|
118 | 118 | # encoding we got. |
|
119 | 119 | nt.assert_equal('test'.encode(encoding), 'test') |
|
120 | 120 | |
|
121 | 121 | |
|
122 | 122 | class NoInputEncodingTestCase(unittest.TestCase): |
|
123 | 123 | def setUp(self): |
|
124 | 124 | self.old_stdin = sys.stdin |
|
125 | 125 | class X: pass |
|
126 | 126 | fake_stdin = X() |
|
127 | 127 | sys.stdin = fake_stdin |
|
128 | 128 | |
|
129 | 129 | def test(self): |
|
130 | 130 | # Verify that if sys.stdin has no 'encoding' attribute we do the right |
|
131 | 131 | # thing |
|
132 | 132 | enc = isp.get_input_encoding() |
|
133 | 133 | self.assertEqual(enc, 'ascii') |
|
134 | 134 | |
|
135 | 135 | def tearDown(self): |
|
136 | 136 | sys.stdin = self.old_stdin |
|
137 | 137 | |
|
138 | 138 | |
|
139 | 139 | class InputSplitterTestCase(unittest.TestCase): |
|
140 | 140 | def setUp(self): |
|
141 | 141 | self.isp = isp.InputSplitter() |
|
142 | 142 | |
|
143 | 143 | def test_reset(self): |
|
144 | 144 | isp = self.isp |
|
145 | 145 | isp.push('x=1') |
|
146 | 146 | isp.reset() |
|
147 | 147 | self.assertEqual(isp._buffer, []) |
|
148 | 148 | self.assertEqual(isp.indent_spaces, 0) |
|
149 | 149 | self.assertEqual(isp.source, '') |
|
150 | 150 | self.assertEqual(isp.code, None) |
|
151 | 151 | self.assertEqual(isp._is_complete, False) |
|
152 | 152 | |
|
153 | 153 | def test_source(self): |
|
154 | 154 | self.isp._store('1') |
|
155 | 155 | self.isp._store('2') |
|
156 | 156 | self.assertEqual(self.isp.source, '1\n2\n') |
|
157 | 157 | self.assertTrue(len(self.isp._buffer)>0) |
|
158 | 158 | self.assertEqual(self.isp.source_reset(), '1\n2\n') |
|
159 | 159 | self.assertEqual(self.isp._buffer, []) |
|
160 | 160 | self.assertEqual(self.isp.source, '') |
|
161 | 161 | |
|
162 | 162 | def test_indent(self): |
|
163 | 163 | isp = self.isp # shorthand |
|
164 | 164 | isp.push('x=1') |
|
165 | 165 | self.assertEqual(isp.indent_spaces, 0) |
|
166 | 166 | isp.push('if 1:\n x=1') |
|
167 | 167 | self.assertEqual(isp.indent_spaces, 4) |
|
168 | 168 | isp.push('y=2\n') |
|
169 | 169 | self.assertEqual(isp.indent_spaces, 0) |
|
170 | 170 | |
|
171 | 171 | def test_indent2(self): |
|
172 | 172 | # In cell mode, inputs must be fed in whole blocks, so skip this test |
|
173 | 173 | if self.isp.input_mode == 'cell': return |
|
174 | 174 | |
|
175 | 175 | isp = self.isp |
|
176 | 176 | isp.push('if 1:') |
|
177 | 177 | self.assertEqual(isp.indent_spaces, 4) |
|
178 | 178 | isp.push(' x=1') |
|
179 | 179 | self.assertEqual(isp.indent_spaces, 4) |
|
180 | 180 | # Blank lines shouldn't change the indent level |
|
181 | 181 | isp.push(' '*2) |
|
182 | 182 | self.assertEqual(isp.indent_spaces, 4) |
|
183 | 183 | |
|
184 | 184 | def test_indent3(self): |
|
185 | 185 | # In cell mode, inputs must be fed in whole blocks, so skip this test |
|
186 | 186 | if self.isp.input_mode == 'cell': return |
|
187 | 187 | |
|
188 | 188 | isp = self.isp |
|
189 | 189 | # When a multiline statement contains parens or multiline strings, we |
|
190 | 190 | # shouldn't get confused. |
|
191 | 191 | isp.push("if 1:") |
|
192 | 192 | isp.push(" x = (1+\n 2)") |
|
193 | 193 | self.assertEqual(isp.indent_spaces, 4) |
|
194 | 194 | |
|
195 | 195 | def test_dedent_pass(self): |
|
196 | 196 | isp = self.isp # shorthand |
|
197 | 197 | # should NOT cause dedent |
|
198 | 198 | isp.push('if 1:\n passes = 5') |
|
199 | 199 | self.assertEqual(isp.indent_spaces, 4) |
|
200 | 200 | isp.push('if 1:\n pass') |
|
201 | 201 | self.assertEqual(isp.indent_spaces, 0) |
|
202 | 202 | isp.push('if 1:\n pass ') |
|
203 | 203 | self.assertEqual(isp.indent_spaces, 0) |
|
204 | 204 | |
|
205 | 205 | def test_dedent_raise(self): |
|
206 | 206 | isp = self.isp # shorthand |
|
207 | 207 | # should NOT cause dedent |
|
208 | 208 | isp.push('if 1:\n raised = 4') |
|
209 | 209 | self.assertEqual(isp.indent_spaces, 4) |
|
210 | 210 | isp.push('if 1:\n raise TypeError()') |
|
211 | 211 | self.assertEqual(isp.indent_spaces, 0) |
|
212 | 212 | isp.push('if 1:\n raise') |
|
213 | 213 | self.assertEqual(isp.indent_spaces, 0) |
|
214 | 214 | isp.push('if 1:\n raise ') |
|
215 | 215 | self.assertEqual(isp.indent_spaces, 0) |
|
216 | 216 | |
|
217 | 217 | def test_dedent_return(self): |
|
218 | 218 | isp = self.isp # shorthand |
|
219 | 219 | # should NOT cause dedent |
|
220 | 220 | isp.push('if 1:\n returning = 4') |
|
221 | 221 | self.assertEqual(isp.indent_spaces, 4) |
|
222 | 222 | isp.push('if 1:\n return 5 + 493') |
|
223 | 223 | self.assertEqual(isp.indent_spaces, 0) |
|
224 | 224 | isp.push('if 1:\n return') |
|
225 | 225 | self.assertEqual(isp.indent_spaces, 0) |
|
226 | 226 | isp.push('if 1:\n return ') |
|
227 | 227 | self.assertEqual(isp.indent_spaces, 0) |
|
228 | 228 | isp.push('if 1:\n return(0)') |
|
229 | 229 | self.assertEqual(isp.indent_spaces, 0) |
|
230 | 230 | |
|
231 | 231 | def test_push(self): |
|
232 | 232 | isp = self.isp |
|
233 | 233 | self.assertTrue(isp.push('x=1')) |
|
234 | 234 | |
|
235 | 235 | def test_push2(self): |
|
236 | 236 | isp = self.isp |
|
237 | 237 | self.assertFalse(isp.push('if 1:')) |
|
238 | 238 | for line in [' x=1', '# a comment', ' y=2']: |
|
239 | 239 | self.assertTrue(isp.push(line)) |
|
240 | 240 | |
|
241 | 241 | def test_push3(self): |
|
242 | 242 | isp = self.isp |
|
243 | 243 | isp.push('if True:') |
|
244 | 244 | isp.push(' a = 1') |
|
245 | 245 | self.assertFalse(isp.push('b = [1,')) |
|
246 | 246 | |
|
247 | 247 | def test_replace_mode(self): |
|
248 | 248 | isp = self.isp |
|
249 | 249 | isp.input_mode = 'cell' |
|
250 | 250 | isp.push('x=1') |
|
251 | 251 | self.assertEqual(isp.source, 'x=1\n') |
|
252 | 252 | isp.push('x=2') |
|
253 | 253 | self.assertEqual(isp.source, 'x=2\n') |
|
254 | 254 | |
|
255 | 255 | def test_push_accepts_more(self): |
|
256 | 256 | isp = self.isp |
|
257 | 257 | isp.push('x=1') |
|
258 | 258 | self.assertFalse(isp.push_accepts_more()) |
|
259 | 259 | |
|
260 | 260 | def test_push_accepts_more2(self): |
|
261 | 261 | # In cell mode, inputs must be fed in whole blocks, so skip this test |
|
262 | 262 | if self.isp.input_mode == 'cell': return |
|
263 | 263 | |
|
264 | 264 | isp = self.isp |
|
265 | 265 | isp.push('if 1:') |
|
266 | 266 | self.assertTrue(isp.push_accepts_more()) |
|
267 | 267 | isp.push(' x=1') |
|
268 | 268 | self.assertTrue(isp.push_accepts_more()) |
|
269 | 269 | isp.push('') |
|
270 | 270 | self.assertFalse(isp.push_accepts_more()) |
|
271 | 271 | |
|
272 | 272 | def test_push_accepts_more3(self): |
|
273 | 273 | isp = self.isp |
|
274 | 274 | isp.push("x = (2+\n3)") |
|
275 | 275 | self.assertFalse(isp.push_accepts_more()) |
|
276 | 276 | |
|
277 | 277 | def test_push_accepts_more4(self): |
|
278 | 278 | # In cell mode, inputs must be fed in whole blocks, so skip this test |
|
279 | 279 | if self.isp.input_mode == 'cell': return |
|
280 | 280 | |
|
281 | 281 | isp = self.isp |
|
282 | 282 | # When a multiline statement contains parens or multiline strings, we |
|
283 | 283 | # shouldn't get confused. |
|
284 | 284 | # FIXME: we should be able to better handle de-dents in statements like |
|
285 | 285 | # multiline strings and multiline expressions (continued with \ or |
|
286 | 286 | # parens). Right now we aren't handling the indentation tracking quite |
|
287 | 287 | # correctly with this, though in practice it may not be too much of a |
|
288 | 288 | # problem. We'll need to see. |
|
289 | 289 | isp.push("if 1:") |
|
290 | 290 | isp.push(" x = (2+") |
|
291 | 291 | isp.push(" 3)") |
|
292 | 292 | self.assertTrue(isp.push_accepts_more()) |
|
293 | 293 | isp.push(" y = 3") |
|
294 | 294 | self.assertTrue(isp.push_accepts_more()) |
|
295 | 295 | isp.push('') |
|
296 | 296 | self.assertFalse(isp.push_accepts_more()) |
|
297 | 297 | |
|
298 | 298 | def test_push_accepts_more5(self): |
|
299 | 299 | # In cell mode, inputs must be fed in whole blocks, so skip this test |
|
300 | 300 | if self.isp.input_mode == 'cell': return |
|
301 | 301 | |
|
302 | 302 | isp = self.isp |
|
303 | 303 | isp.push('try:') |
|
304 | 304 | isp.push(' a = 5') |
|
305 | 305 | isp.push('except:') |
|
306 | 306 | isp.push(' raise') |
|
307 | 307 | self.assertTrue(isp.push_accepts_more()) |
|
308 | 308 | |
|
309 | 309 | def test_continuation(self): |
|
310 | 310 | isp = self.isp |
|
311 | 311 | isp.push("import os, \\") |
|
312 | 312 | self.assertTrue(isp.push_accepts_more()) |
|
313 | 313 | isp.push("sys") |
|
314 | 314 | self.assertFalse(isp.push_accepts_more()) |
|
315 | 315 | |
|
316 | 316 | def test_syntax_error(self): |
|
317 | 317 | isp = self.isp |
|
318 | 318 | # Syntax errors immediately produce a 'ready' block, so the invalid |
|
319 | 319 | # Python can be sent to the kernel for evaluation with possible ipython |
|
320 | 320 | # special-syntax conversion. |
|
321 | 321 | isp.push('run foo') |
|
322 | 322 | self.assertFalse(isp.push_accepts_more()) |
|
323 | 323 | |
|
324 | 324 | def test_unicode(self): |
|
325 | 325 | self.isp.push(u"PΓ©rez") |
|
326 | 326 | self.isp.push(u'\xc3\xa9') |
|
327 | 327 | self.isp.push(u"u'\xc3\xa9'") |
|
328 | 328 | |
|
329 | 329 | class InteractiveLoopTestCase(unittest.TestCase): |
|
330 | 330 | """Tests for an interactive loop like a python shell. |
|
331 | 331 | """ |
|
332 | 332 | def check_ns(self, lines, ns): |
|
333 | 333 | """Validate that the given input lines produce the resulting namespace. |
|
334 | 334 | |
|
335 | 335 | Note: the input lines are given exactly as they would be typed in an |
|
336 | 336 | auto-indenting environment, as mini_interactive_loop above already does |
|
337 | 337 | auto-indenting and prepends spaces to the input. |
|
338 | 338 | """ |
|
339 | 339 | src = mini_interactive_loop(pseudo_input(lines)) |
|
340 | 340 | test_ns = {} |
|
341 | 341 | exec src in test_ns |
|
342 | 342 | # We can't check that the provided ns is identical to the test_ns, |
|
343 | 343 | # because Python fills test_ns with extra keys (copyright, etc). But |
|
344 | 344 | # we can check that the given dict is *contained* in test_ns |
|
345 | 345 | for k,v in ns.iteritems(): |
|
346 | 346 | self.assertEqual(test_ns[k], v) |
|
347 | 347 | |
|
348 | 348 | def test_simple(self): |
|
349 | 349 | self.check_ns(['x=1'], dict(x=1)) |
|
350 | 350 | |
|
351 | 351 | def test_simple2(self): |
|
352 | 352 | self.check_ns(['if 1:', 'x=2'], dict(x=2)) |
|
353 | 353 | |
|
354 | 354 | def test_xy(self): |
|
355 | 355 | self.check_ns(['x=1; y=2'], dict(x=1, y=2)) |
|
356 | 356 | |
|
357 | 357 | def test_abc(self): |
|
358 | 358 | self.check_ns(['if 1:','a=1','b=2','c=3'], dict(a=1, b=2, c=3)) |
|
359 | 359 | |
|
360 | 360 | def test_multi(self): |
|
361 | 361 | self.check_ns(['x =(1+','1+','2)'], dict(x=4)) |
|
362 | 362 | |
|
363 | 363 | |
|
364 | 364 | def test_LineInfo(): |
|
365 | 365 | """Simple test for LineInfo construction and str()""" |
|
366 | 366 | linfo = isp.LineInfo(' %cd /home') |
|
367 | 367 | nt.assert_equals(str(linfo), 'LineInfo [ |%|cd|/home]') |
|
368 | 368 | |
|
369 | 369 | |
|
370 | 370 | def test_split_user_input(): |
|
371 | 371 | """Unicode test - split_user_input already has good doctests""" |
|
372 | 372 | line = u"PΓ©rez Fernando" |
|
373 | 373 | parts = isp.split_user_input(line) |
|
374 | 374 | parts_expected = (u'', u'', u'', line) |
|
375 | 375 | nt.assert_equal(parts, parts_expected) |
|
376 | 376 | |
|
377 | 377 | |
|
378 | 378 | # Transformer tests |
|
379 | 379 | def transform_checker(tests, func): |
|
380 | 380 | """Utility to loop over test inputs""" |
|
381 | 381 | for inp, tr in tests: |
|
382 | 382 | nt.assert_equals(func(inp), tr) |
|
383 | 383 | |
|
384 | 384 | # Data for all the syntax tests in the form of lists of pairs of |
|
385 | 385 | # raw/transformed input. We store it here as a global dict so that we can use |
|
386 | 386 | # it both within single-function tests and also to validate the behavior of the |
|
387 | 387 | # larger objects |
|
388 | 388 | |
|
389 | 389 | syntax = \ |
|
390 | 390 | dict(assign_system = |
|
391 | 391 | [('a =! ls', 'a = get_ipython().getoutput(u"ls")'), |
|
392 | 392 | ('b = !ls', 'b = get_ipython().getoutput(u"ls")'), |
|
393 | 393 | ('x=1', 'x=1'), # normal input is unmodified |
|
394 | 394 | (' ',' '), # blank lines are kept intact |
|
395 | 395 | ], |
|
396 | 396 | |
|
397 | 397 | assign_magic = |
|
398 | 398 | [('a =% who', 'a = get_ipython().magic(u"who")'), |
|
399 | 399 | ('b = %who', 'b = get_ipython().magic(u"who")'), |
|
400 | 400 | ('x=1', 'x=1'), # normal input is unmodified |
|
401 | 401 | (' ',' '), # blank lines are kept intact |
|
402 | 402 | ], |
|
403 | 403 | |
|
404 | 404 | classic_prompt = |
|
405 | 405 | [('>>> x=1', 'x=1'), |
|
406 | 406 | ('x=1', 'x=1'), # normal input is unmodified |
|
407 | 407 | (' ', ' '), # blank lines are kept intact |
|
408 | 408 | ('... ', ''), # continuation prompts |
|
409 | 409 | ], |
|
410 | 410 | |
|
411 | 411 | ipy_prompt = |
|
412 | 412 | [('In [1]: x=1', 'x=1'), |
|
413 | 413 | ('x=1', 'x=1'), # normal input is unmodified |
|
414 | 414 | (' ',' '), # blank lines are kept intact |
|
415 | 415 | (' ....: ', ''), # continuation prompts |
|
416 | 416 | ], |
|
417 | 417 | |
|
418 | 418 | # Tests for the escape transformer to leave normal code alone |
|
419 | 419 | escaped_noesc = |
|
420 | 420 | [ (' ', ' '), |
|
421 | 421 | ('x=1', 'x=1'), |
|
422 | 422 | ], |
|
423 | 423 | |
|
424 | 424 | # System calls |
|
425 | 425 | escaped_shell = |
|
426 | 426 | [ ('!ls', 'get_ipython().system(u"ls")'), |
|
427 | 427 | # Double-escape shell, this means to capture the output of the |
|
428 | 428 | # subprocess and return it |
|
429 | 429 | ('!!ls', 'get_ipython().getoutput(u"ls")'), |
|
430 | 430 | ], |
|
431 | 431 | |
|
432 | 432 | # Help/object info |
|
433 | 433 | escaped_help = |
|
434 | 434 | [ ('?', 'get_ipython().show_usage()'), |
|
435 | 435 | ('?x1', 'get_ipython().magic(u"pinfo x1")'), |
|
436 | 436 | ('??x2', 'get_ipython().magic(u"pinfo2 x2")'), |
|
437 | 437 | ('?a.*s', 'get_ipython().magic(u"psearch a.*s")'), |
|
438 | 438 | ('?%hist', 'get_ipython().magic(u"pinfo %hist")'), |
|
439 | 439 | ('?abc = qwe', 'get_ipython().magic(u"pinfo abc")'), |
|
440 | 440 | ], |
|
441 | 441 | |
|
442 | 442 | end_help = |
|
443 | 443 | [ ('x3?', 'get_ipython().magic(u"pinfo x3")'), |
|
444 | 444 | ('x4??', 'get_ipython().magic(u"pinfo2 x4")'), |
|
445 | 445 | ('%hist?', 'get_ipython().magic(u"pinfo %hist")'), |
|
446 | 446 | ('f*?', 'get_ipython().magic(u"psearch f*")'), |
|
447 | 447 | ('ax.*aspe*?', 'get_ipython().magic(u"psearch ax.*aspe*")'), |
|
448 | 448 | ('a = abc?', 'get_ipython().magic(u"pinfo abc")'), |
|
449 | 449 | ('a = abc.qe??', 'get_ipython().magic(u"pinfo2 abc.qe")'), |
|
450 | 450 | ('a = *.items?', 'get_ipython().magic(u"psearch *.items")'), |
|
451 | 451 | ], |
|
452 | 452 | |
|
453 | 453 | # Explicit magic calls |
|
454 | 454 | escaped_magic = |
|
455 | 455 | [ ('%cd', 'get_ipython().magic(u"cd")'), |
|
456 | 456 | ('%cd /home', 'get_ipython().magic(u"cd /home")'), |
|
457 | 457 | (' %magic', ' get_ipython().magic(u"magic")'), |
|
458 | 458 | ], |
|
459 | 459 | |
|
460 | 460 | # Quoting with separate arguments |
|
461 | 461 | escaped_quote = |
|
462 | 462 | [ (',f', 'f("")'), |
|
463 | 463 | (',f x', 'f("x")'), |
|
464 | 464 | (' ,f y', ' f("y")'), |
|
465 | 465 | (',f a b', 'f("a", "b")'), |
|
466 | 466 | ], |
|
467 | 467 | |
|
468 | 468 | # Quoting with single argument |
|
469 | 469 | escaped_quote2 = |
|
470 | 470 | [ (';f', 'f("")'), |
|
471 | 471 | (';f x', 'f("x")'), |
|
472 | 472 | (' ;f y', ' f("y")'), |
|
473 | 473 | (';f a b', 'f("a b")'), |
|
474 | 474 | ], |
|
475 | 475 | |
|
476 | 476 | # Simply apply parens |
|
477 | 477 | escaped_paren = |
|
478 | 478 | [ ('/f', 'f()'), |
|
479 | 479 | ('/f x', 'f(x)'), |
|
480 | 480 | (' /f y', ' f(y)'), |
|
481 | 481 | ('/f a b', 'f(a, b)'), |
|
482 | 482 | ], |
|
483 | 483 | |
|
484 | # Check that we transform prompts before other transforms | |
|
485 | mixed = | |
|
486 | [ ('In [1]: %lsmagic', 'get_ipython().magic(u"lsmagic")'), | |
|
487 | ('>>> %lsmagic', 'get_ipython().magic(u"lsmagic")'), | |
|
488 | ('In [2]: !ls', 'get_ipython().system(u"ls")'), | |
|
489 | ('In [3]: abs?', 'get_ipython().magic(u"pinfo abs")'), | |
|
490 | ('In [4]: b = %who', 'b = get_ipython().magic(u"who")'), | |
|
491 | ], | |
|
484 | 492 | ) |
|
485 | 493 | |
|
486 | 494 | # multiline syntax examples. Each of these should be a list of lists, with |
|
487 | 495 | # each entry itself having pairs of raw/transformed input. The union (with |
|
488 | 496 | # '\n'.join() of the transformed inputs is what the splitter should produce |
|
489 | 497 | # when fed the raw lines one at a time via push. |
|
490 | 498 | syntax_ml = \ |
|
491 | 499 | dict(classic_prompt = |
|
492 | 500 | [ [('>>> for i in range(10):','for i in range(10):'), |
|
493 | 501 | ('... print i',' print i'), |
|
494 | 502 | ('... ', ''), |
|
495 | 503 | ], |
|
496 | 504 | ], |
|
497 | 505 | |
|
498 | 506 | ipy_prompt = |
|
499 | 507 | [ [('In [24]: for i in range(10):','for i in range(10):'), |
|
500 | 508 | (' ....: print i',' print i'), |
|
501 | 509 | (' ....: ', ''), |
|
502 | 510 | ], |
|
503 | 511 | ], |
|
504 | 512 | ) |
|
505 | 513 | |
|
506 | 514 | |
|
507 | 515 | def test_assign_system(): |
|
508 | 516 | transform_checker(syntax['assign_system'], isp.transform_assign_system) |
|
509 | 517 | |
|
510 | 518 | |
|
511 | 519 | def test_assign_magic(): |
|
512 | 520 | transform_checker(syntax['assign_magic'], isp.transform_assign_magic) |
|
513 | 521 | |
|
514 | 522 | |
|
515 | 523 | def test_classic_prompt(): |
|
516 | 524 | transform_checker(syntax['classic_prompt'], isp.transform_classic_prompt) |
|
517 | 525 | for example in syntax_ml['classic_prompt']: |
|
518 | 526 | transform_checker(example, isp.transform_classic_prompt) |
|
519 | 527 | |
|
520 | 528 | |
|
521 | 529 | def test_ipy_prompt(): |
|
522 | 530 | transform_checker(syntax['ipy_prompt'], isp.transform_ipy_prompt) |
|
523 | 531 | for example in syntax_ml['ipy_prompt']: |
|
524 | 532 | transform_checker(example, isp.transform_ipy_prompt) |
|
525 | 533 | |
|
526 | 534 | def test_end_help(): |
|
527 | 535 | transform_checker(syntax['end_help'], isp.transform_help_end) |
|
528 | 536 | |
|
529 | 537 | def test_escaped_noesc(): |
|
530 | 538 | transform_checker(syntax['escaped_noesc'], isp.transform_escaped) |
|
531 | 539 | |
|
532 | 540 | |
|
533 | 541 | def test_escaped_shell(): |
|
534 | 542 | transform_checker(syntax['escaped_shell'], isp.transform_escaped) |
|
535 | 543 | |
|
536 | 544 | |
|
537 | 545 | def test_escaped_help(): |
|
538 | 546 | transform_checker(syntax['escaped_help'], isp.transform_escaped) |
|
539 | 547 | |
|
540 | 548 | |
|
541 | 549 | def test_escaped_magic(): |
|
542 | 550 | transform_checker(syntax['escaped_magic'], isp.transform_escaped) |
|
543 | 551 | |
|
544 | 552 | |
|
545 | 553 | def test_escaped_quote(): |
|
546 | 554 | transform_checker(syntax['escaped_quote'], isp.transform_escaped) |
|
547 | 555 | |
|
548 | 556 | |
|
549 | 557 | def test_escaped_quote2(): |
|
550 | 558 | transform_checker(syntax['escaped_quote2'], isp.transform_escaped) |
|
551 | 559 | |
|
552 | 560 | |
|
553 | 561 | def test_escaped_paren(): |
|
554 | 562 | transform_checker(syntax['escaped_paren'], isp.transform_escaped) |
|
555 | 563 | |
|
556 | 564 | |
|
557 | 565 | class IPythonInputTestCase(InputSplitterTestCase): |
|
558 | 566 | """By just creating a new class whose .isp is a different instance, we |
|
559 | 567 | re-run the same test battery on the new input splitter. |
|
560 | 568 | |
|
561 | 569 | In addition, this runs the tests over the syntax and syntax_ml dicts that |
|
562 | 570 | were tested by individual functions, as part of the OO interface. |
|
563 | 571 | |
|
564 | 572 | It also makes some checks on the raw buffer storage. |
|
565 | 573 | """ |
|
566 | 574 | |
|
567 | 575 | def setUp(self): |
|
568 | 576 | self.isp = isp.IPythonInputSplitter(input_mode='line') |
|
569 | 577 | |
|
570 | 578 | def test_syntax(self): |
|
571 | 579 | """Call all single-line syntax tests from the main object""" |
|
572 | 580 | isp = self.isp |
|
573 | 581 | for example in syntax.itervalues(): |
|
574 | 582 | for raw, out_t in example: |
|
575 | 583 | if raw.startswith(' '): |
|
576 | 584 | continue |
|
577 | 585 | |
|
578 | 586 | isp.push(raw) |
|
579 | 587 | out, out_raw = isp.source_raw_reset() |
|
580 | 588 | self.assertEqual(out.rstrip(), out_t) |
|
581 | 589 | self.assertEqual(out_raw.rstrip(), raw.rstrip()) |
|
582 | 590 | |
|
583 | 591 | def test_syntax_multiline(self): |
|
584 | 592 | isp = self.isp |
|
585 | 593 | for example in syntax_ml.itervalues(): |
|
586 | 594 | out_t_parts = [] |
|
587 | 595 | raw_parts = [] |
|
588 | 596 | for line_pairs in example: |
|
589 | 597 | for lraw, out_t_part in line_pairs: |
|
590 | 598 | isp.push(lraw) |
|
591 | 599 | out_t_parts.append(out_t_part) |
|
592 | 600 | raw_parts.append(lraw) |
|
593 | 601 | |
|
594 | 602 | out, out_raw = isp.source_raw_reset() |
|
595 | 603 | out_t = '\n'.join(out_t_parts).rstrip() |
|
596 | 604 | raw = '\n'.join(raw_parts).rstrip() |
|
597 | 605 | self.assertEqual(out.rstrip(), out_t) |
|
598 | 606 | self.assertEqual(out_raw.rstrip(), raw) |
|
599 | 607 | |
|
600 | 608 | |
|
601 | 609 | class BlockIPythonInputTestCase(IPythonInputTestCase): |
|
602 | 610 | |
|
603 | 611 | # Deactivate tests that don't make sense for the block mode |
|
604 | 612 | test_push3 = test_split = lambda s: None |
|
605 | 613 | |
|
606 | 614 | def setUp(self): |
|
607 | 615 | self.isp = isp.IPythonInputSplitter(input_mode='cell') |
|
608 | 616 | |
|
609 | 617 | def test_syntax_multiline(self): |
|
610 | 618 | isp = self.isp |
|
611 | 619 | for example in syntax_ml.itervalues(): |
|
612 | 620 | raw_parts = [] |
|
613 | 621 | out_t_parts = [] |
|
614 | 622 | for line_pairs in example: |
|
615 | 623 | for raw, out_t_part in line_pairs: |
|
616 | 624 | raw_parts.append(raw) |
|
617 | 625 | out_t_parts.append(out_t_part) |
|
618 | 626 | |
|
619 | 627 | raw = '\n'.join(raw_parts) |
|
620 | 628 | out_t = '\n'.join(out_t_parts) |
|
621 | 629 | |
|
622 | 630 | isp.push(raw) |
|
623 | 631 | out, out_raw = isp.source_raw_reset() |
|
624 | 632 | # Match ignoring trailing whitespace |
|
625 | 633 | self.assertEqual(out.rstrip(), out_t.rstrip()) |
|
626 | 634 | self.assertEqual(out_raw.rstrip(), raw.rstrip()) |
|
627 | 635 | |
|
628 | 636 | |
|
629 | 637 | #----------------------------------------------------------------------------- |
|
630 | 638 | # Main - use as a script, mostly for developer experiments |
|
631 | 639 | #----------------------------------------------------------------------------- |
|
632 | 640 | |
|
633 | 641 | if __name__ == '__main__': |
|
634 | 642 | # A simple demo for interactive experimentation. This code will not get |
|
635 | 643 | # picked up by any test suite. |
|
636 | 644 | from IPython.core.inputsplitter import InputSplitter, IPythonInputSplitter |
|
637 | 645 | |
|
638 | 646 | # configure here the syntax to use, prompt and whether to autoindent |
|
639 | 647 | #isp, start_prompt = InputSplitter(), '>>> ' |
|
640 | 648 | isp, start_prompt = IPythonInputSplitter(), 'In> ' |
|
641 | 649 | |
|
642 | 650 | autoindent = True |
|
643 | 651 | #autoindent = False |
|
644 | 652 | |
|
645 | 653 | try: |
|
646 | 654 | while True: |
|
647 | 655 | prompt = start_prompt |
|
648 | 656 | while isp.push_accepts_more(): |
|
649 | 657 | indent = ' '*isp.indent_spaces |
|
650 | 658 | if autoindent: |
|
651 | 659 | line = indent + raw_input(prompt+indent) |
|
652 | 660 | else: |
|
653 | 661 | line = raw_input(prompt) |
|
654 | 662 | isp.push(line) |
|
655 | 663 | prompt = '... ' |
|
656 | 664 | |
|
657 | 665 | # Here we just return input so we can use it in a test suite, but a |
|
658 | 666 | # real interpreter would instead send it for execution somewhere. |
|
659 | 667 | #src = isp.source; raise EOFError # dbg |
|
660 | 668 | src, raw = isp.source_raw_reset() |
|
661 | 669 | print 'Input source was:\n', src |
|
662 | 670 | print 'Raw source was:\n', raw |
|
663 | 671 | except EOFError: |
|
664 | 672 | print 'Bye' |
General Comments 0
You need to be logged in to leave comments.
Login now