Show More
@@ -1,907 +1,913 b'' | |||
|
1 | 1 | """ History related magics and functionality """ |
|
2 | 2 | |
|
3 | 3 | # Copyright (c) IPython Development Team. |
|
4 | 4 | # Distributed under the terms of the Modified BSD License. |
|
5 | 5 | |
|
6 | 6 | |
|
7 | 7 | import atexit |
|
8 | 8 | import datetime |
|
9 | 9 | from pathlib import Path |
|
10 | 10 | import re |
|
11 | 11 | import sqlite3 |
|
12 | 12 | import threading |
|
13 | 13 | |
|
14 | 14 | from traitlets.config.configurable import LoggingConfigurable |
|
15 | 15 | from decorator import decorator |
|
16 | 16 | from IPython.utils.decorators import undoc |
|
17 | 17 | from IPython.paths import locate_profile |
|
18 | 18 | from traitlets import ( |
|
19 | 19 | Any, |
|
20 | 20 | Bool, |
|
21 | 21 | Dict, |
|
22 | 22 | Instance, |
|
23 | 23 | Integer, |
|
24 | 24 | List, |
|
25 | 25 | Unicode, |
|
26 | 26 | Union, |
|
27 | 27 | TraitError, |
|
28 | 28 | default, |
|
29 | 29 | observe, |
|
30 | 30 | ) |
|
31 | 31 | |
|
32 | 32 | #----------------------------------------------------------------------------- |
|
33 | 33 | # Classes and functions |
|
34 | 34 | #----------------------------------------------------------------------------- |
|
35 | 35 | |
|
36 | 36 | @undoc |
|
37 | 37 | class DummyDB(object): |
|
38 | 38 | """Dummy DB that will act as a black hole for history. |
|
39 | 39 | |
|
40 | 40 | Only used in the absence of sqlite""" |
|
41 | 41 | def execute(*args, **kwargs): |
|
42 | 42 | return [] |
|
43 | 43 | |
|
44 | 44 | def commit(self, *args, **kwargs): |
|
45 | 45 | pass |
|
46 | 46 | |
|
47 | 47 | def __enter__(self, *args, **kwargs): |
|
48 | 48 | pass |
|
49 | 49 | |
|
50 | 50 | def __exit__(self, *args, **kwargs): |
|
51 | 51 | pass |
|
52 | 52 | |
|
53 | 53 | |
|
54 | 54 | @decorator |
|
55 | 55 | def only_when_enabled(f, self, *a, **kw): |
|
56 | 56 | """Decorator: return an empty list in the absence of sqlite.""" |
|
57 | 57 | if not self.enabled: |
|
58 | 58 | return [] |
|
59 | 59 | else: |
|
60 | 60 | return f(self, *a, **kw) |
|
61 | 61 | |
|
62 | 62 | |
|
63 | 63 | # use 16kB as threshold for whether a corrupt history db should be saved |
|
64 | 64 | # that should be at least 100 entries or so |
|
65 | 65 | _SAVE_DB_SIZE = 16384 |
|
66 | 66 | |
|
67 | 67 | @decorator |
|
68 | 68 | def catch_corrupt_db(f, self, *a, **kw): |
|
69 | 69 | """A decorator which wraps HistoryAccessor method calls to catch errors from |
|
70 | 70 | a corrupt SQLite database, move the old database out of the way, and create |
|
71 | 71 | a new one. |
|
72 | 72 | |
|
73 | 73 | We avoid clobbering larger databases because this may be triggered due to filesystem issues, |
|
74 | 74 | not just a corrupt file. |
|
75 | 75 | """ |
|
76 | 76 | try: |
|
77 | 77 | return f(self, *a, **kw) |
|
78 | 78 | except (sqlite3.DatabaseError, sqlite3.OperationalError) as e: |
|
79 | 79 | self._corrupt_db_counter += 1 |
|
80 | 80 | self.log.error("Failed to open SQLite history %s (%s).", self.hist_file, e) |
|
81 | 81 | if self.hist_file != ':memory:': |
|
82 | 82 | if self._corrupt_db_counter > self._corrupt_db_limit: |
|
83 | 83 | self.hist_file = ':memory:' |
|
84 | 84 | self.log.error("Failed to load history too many times, history will not be saved.") |
|
85 | 85 | elif self.hist_file.is_file(): |
|
86 | 86 | # move the file out of the way |
|
87 | 87 | base = str(self.hist_file.parent / self.hist_file.stem) |
|
88 | 88 | ext = self.hist_file.suffix |
|
89 | 89 | size = self.hist_file.stat().st_size |
|
90 | 90 | if size >= _SAVE_DB_SIZE: |
|
91 | 91 | # if there's significant content, avoid clobbering |
|
92 | 92 | now = datetime.datetime.now().isoformat().replace(':', '.') |
|
93 | 93 | newpath = base + '-corrupt-' + now + ext |
|
94 | 94 | # don't clobber previous corrupt backups |
|
95 | 95 | for i in range(100): |
|
96 | 96 | if not Path(newpath).exists(): |
|
97 | 97 | break |
|
98 | 98 | else: |
|
99 | 99 | newpath = base + '-corrupt-' + now + (u'-%i' % i) + ext |
|
100 | 100 | else: |
|
101 | 101 | # not much content, possibly empty; don't worry about clobbering |
|
102 | 102 | # maybe we should just delete it? |
|
103 | 103 | newpath = base + '-corrupt' + ext |
|
104 | 104 | self.hist_file.rename(newpath) |
|
105 | 105 | self.log.error("History file was moved to %s and a new file created.", newpath) |
|
106 | 106 | self.init_db() |
|
107 | 107 | return [] |
|
108 | 108 | else: |
|
109 | 109 | # Failed with :memory:, something serious is wrong |
|
110 | 110 | raise |
|
111 | 111 | |
|
112 | 112 | |
|
113 | 113 | class HistoryAccessorBase(LoggingConfigurable): |
|
114 | 114 | """An abstract class for History Accessors """ |
|
115 | 115 | |
|
116 | 116 | def get_tail(self, n=10, raw=True, output=False, include_latest=False): |
|
117 | 117 | raise NotImplementedError |
|
118 | 118 | |
|
119 | 119 | def search(self, pattern="*", raw=True, search_raw=True, |
|
120 | 120 | output=False, n=None, unique=False): |
|
121 | 121 | raise NotImplementedError |
|
122 | 122 | |
|
123 | 123 | def get_range(self, session, start=1, stop=None, raw=True,output=False): |
|
124 | 124 | raise NotImplementedError |
|
125 | 125 | |
|
126 | 126 | def get_range_by_str(self, rangestr, raw=True, output=False): |
|
127 | 127 | raise NotImplementedError |
|
128 | 128 | |
|
129 | 129 | |
|
130 | 130 | class HistoryAccessor(HistoryAccessorBase): |
|
131 | 131 | """Access the history database without adding to it. |
|
132 | 132 | |
|
133 | 133 | This is intended for use by standalone history tools. IPython shells use |
|
134 | 134 | HistoryManager, below, which is a subclass of this.""" |
|
135 | 135 | |
|
136 | 136 | # counter for init_db retries, so we don't keep trying over and over |
|
137 | 137 | _corrupt_db_counter = 0 |
|
138 | 138 | # after two failures, fallback on :memory: |
|
139 | 139 | _corrupt_db_limit = 2 |
|
140 | 140 | |
|
141 | 141 | # String holding the path to the history file |
|
142 | 142 | hist_file = Union( |
|
143 | 143 | [Instance(Path), Unicode()], |
|
144 | 144 | help="""Path to file to use for SQLite history database. |
|
145 | 145 | |
|
146 | 146 | By default, IPython will put the history database in the IPython |
|
147 | 147 | profile directory. If you would rather share one history among |
|
148 | 148 | profiles, you can set this value in each, so that they are consistent. |
|
149 | 149 | |
|
150 | 150 | Due to an issue with fcntl, SQLite is known to misbehave on some NFS |
|
151 | 151 | mounts. If you see IPython hanging, try setting this to something on a |
|
152 | 152 | local disk, e.g:: |
|
153 | 153 | |
|
154 | 154 | ipython --HistoryManager.hist_file=/tmp/ipython_hist.sqlite |
|
155 | 155 | |
|
156 | 156 | you can also use the specific value `:memory:` (including the colon |
|
157 | 157 | at both end but not the back ticks), to avoid creating an history file. |
|
158 | 158 | |
|
159 | 159 | """, |
|
160 | 160 | ).tag(config=True) |
|
161 | 161 | |
|
162 | 162 | enabled = Bool(True, |
|
163 | 163 | help="""enable the SQLite history |
|
164 | 164 | |
|
165 | 165 | set enabled=False to disable the SQLite history, |
|
166 | 166 | in which case there will be no stored history, no SQLite connection, |
|
167 | 167 | and no background saving thread. This may be necessary in some |
|
168 | 168 | threaded environments where IPython is embedded. |
|
169 | 169 | """ |
|
170 | 170 | ).tag(config=True) |
|
171 | 171 | |
|
172 | 172 | connection_options = Dict( |
|
173 | 173 | help="""Options for configuring the SQLite connection |
|
174 | 174 | |
|
175 | 175 | These options are passed as keyword args to sqlite3.connect |
|
176 | 176 | when establishing database connections. |
|
177 | 177 | """ |
|
178 | 178 | ).tag(config=True) |
|
179 | 179 | |
|
180 | 180 | # The SQLite database |
|
181 | 181 | db = Any() |
|
182 | 182 | @observe('db') |
|
183 | 183 | def _db_changed(self, change): |
|
184 | 184 | """validate the db, since it can be an Instance of two different types""" |
|
185 | 185 | new = change['new'] |
|
186 | 186 | connection_types = (DummyDB, sqlite3.Connection) |
|
187 | 187 | if not isinstance(new, connection_types): |
|
188 | 188 | msg = "%s.db must be sqlite3 Connection or DummyDB, not %r" % \ |
|
189 | 189 | (self.__class__.__name__, new) |
|
190 | 190 | raise TraitError(msg) |
|
191 | 191 | |
|
192 | 192 | def __init__(self, profile="default", hist_file="", **traits): |
|
193 | 193 | """Create a new history accessor. |
|
194 | 194 | |
|
195 | 195 | Parameters |
|
196 | 196 | ---------- |
|
197 | 197 | profile : str |
|
198 | 198 | The name of the profile from which to open history. |
|
199 | 199 | hist_file : str |
|
200 | 200 | Path to an SQLite history database stored by IPython. If specified, |
|
201 | 201 | hist_file overrides profile. |
|
202 | 202 | config : :class:`~traitlets.config.loader.Config` |
|
203 | 203 | Config object. hist_file can also be set through this. |
|
204 | 204 | """ |
|
205 | 205 | # We need a pointer back to the shell for various tasks. |
|
206 | 206 | super(HistoryAccessor, self).__init__(**traits) |
|
207 | 207 | # defer setting hist_file from kwarg until after init, |
|
208 | 208 | # otherwise the default kwarg value would clobber any value |
|
209 | 209 | # set by config |
|
210 | 210 | if hist_file: |
|
211 | 211 | self.hist_file = hist_file |
|
212 | 212 | |
|
213 | 213 | try: |
|
214 | 214 | self.hist_file |
|
215 | 215 | except TraitError: |
|
216 | 216 | # No one has set the hist_file, yet. |
|
217 | 217 | self.hist_file = self._get_hist_file_name(profile) |
|
218 | 218 | |
|
219 | 219 | self.init_db() |
|
220 | 220 | |
|
221 | 221 | def _get_hist_file_name(self, profile='default'): |
|
222 | 222 | """Find the history file for the given profile name. |
|
223 | 223 | |
|
224 | 224 | This is overridden by the HistoryManager subclass, to use the shell's |
|
225 | 225 | active profile. |
|
226 | 226 | |
|
227 | 227 | Parameters |
|
228 | 228 | ---------- |
|
229 | 229 | profile : str |
|
230 | 230 | The name of a profile which has a history file. |
|
231 | 231 | """ |
|
232 | 232 | return Path(locate_profile(profile)) / "history.sqlite" |
|
233 | 233 | |
|
234 | 234 | @catch_corrupt_db |
|
235 | 235 | def init_db(self): |
|
236 | 236 | """Connect to the database, and create tables if necessary.""" |
|
237 | 237 | if not self.enabled: |
|
238 | 238 | self.db = DummyDB() |
|
239 | 239 | return |
|
240 | 240 | |
|
241 | 241 | # use detect_types so that timestamps return datetime objects |
|
242 | 242 | kwargs = dict(detect_types=sqlite3.PARSE_DECLTYPES|sqlite3.PARSE_COLNAMES) |
|
243 | 243 | kwargs.update(self.connection_options) |
|
244 | 244 | self.db = sqlite3.connect(str(self.hist_file), **kwargs) |
|
245 | self.db.execute("""CREATE TABLE IF NOT EXISTS sessions (session integer | |
|
246 | primary key autoincrement, start timestamp, | |
|
247 | end timestamp, num_cmds integer, remark text)""") | |
|
248 | self.db.execute("""CREATE TABLE IF NOT EXISTS history | |
|
249 | (session integer, line integer, source text, source_raw text, | |
|
250 | PRIMARY KEY (session, line))""") | |
|
251 | # Output history is optional, but ensure the table's there so it can be | |
|
252 | # enabled later. | |
|
253 | self.db.execute("""CREATE TABLE IF NOT EXISTS output_history | |
|
254 |
|
|
|
255 | PRIMARY KEY (session, line))""") | |
|
256 | self.db.commit() | |
|
245 | with self.db: | |
|
246 | self.db.execute( | |
|
247 | """CREATE TABLE IF NOT EXISTS sessions (session integer | |
|
248 | primary key autoincrement, start timestamp, | |
|
249 | end timestamp, num_cmds integer, remark text)""" | |
|
250 | ) | |
|
251 | self.db.execute( | |
|
252 | """CREATE TABLE IF NOT EXISTS history | |
|
253 | (session integer, line integer, source text, source_raw text, | |
|
254 | PRIMARY KEY (session, line))""" | |
|
255 | ) | |
|
256 | # Output history is optional, but ensure the table's there so it can be | |
|
257 | # enabled later. | |
|
258 | self.db.execute( | |
|
259 | """CREATE TABLE IF NOT EXISTS output_history | |
|
260 | (session integer, line integer, output text, | |
|
261 | PRIMARY KEY (session, line))""" | |
|
262 | ) | |
|
257 | 263 | # success! reset corrupt db count |
|
258 | 264 | self._corrupt_db_counter = 0 |
|
259 | 265 | |
|
260 | 266 | def writeout_cache(self): |
|
261 | 267 | """Overridden by HistoryManager to dump the cache before certain |
|
262 | 268 | database lookups.""" |
|
263 | 269 | pass |
|
264 | 270 | |
|
265 | 271 | ## ------------------------------- |
|
266 | 272 | ## Methods for retrieving history: |
|
267 | 273 | ## ------------------------------- |
|
268 | 274 | def _run_sql(self, sql, params, raw=True, output=False, latest=False): |
|
269 | 275 | """Prepares and runs an SQL query for the history database. |
|
270 | 276 | |
|
271 | 277 | Parameters |
|
272 | 278 | ---------- |
|
273 | 279 | sql : str |
|
274 | 280 | Any filtering expressions to go after SELECT ... FROM ... |
|
275 | 281 | params : tuple |
|
276 | 282 | Parameters passed to the SQL query (to replace "?") |
|
277 | 283 | raw, output : bool |
|
278 | 284 | See :meth:`get_range` |
|
279 | 285 | latest : bool |
|
280 | 286 | Select rows with max (session, line) |
|
281 | 287 | |
|
282 | 288 | Returns |
|
283 | 289 | ------- |
|
284 | 290 | Tuples as :meth:`get_range` |
|
285 | 291 | """ |
|
286 | 292 | toget = 'source_raw' if raw else 'source' |
|
287 | 293 | sqlfrom = "history" |
|
288 | 294 | if output: |
|
289 | 295 | sqlfrom = "history LEFT JOIN output_history USING (session, line)" |
|
290 | 296 | toget = "history.%s, output_history.output" % toget |
|
291 | 297 | if latest: |
|
292 | 298 | toget += ", MAX(session * 128 * 1024 + line)" |
|
293 | 299 | cur = self.db.execute("SELECT session, line, %s FROM %s " %\ |
|
294 | 300 | (toget, sqlfrom) + sql, params) |
|
295 | 301 | if latest: |
|
296 | 302 | cur = (row[:-1] for row in cur) |
|
297 | 303 | if output: # Regroup into 3-tuples, and parse JSON |
|
298 | 304 | return ((ses, lin, (inp, out)) for ses, lin, inp, out in cur) |
|
299 | 305 | return cur |
|
300 | 306 | |
|
301 | 307 | @only_when_enabled |
|
302 | 308 | @catch_corrupt_db |
|
303 | 309 | def get_session_info(self, session): |
|
304 | 310 | """Get info about a session. |
|
305 | 311 | |
|
306 | 312 | Parameters |
|
307 | 313 | ---------- |
|
308 | 314 | session : int |
|
309 | 315 | Session number to retrieve. |
|
310 | 316 | |
|
311 | 317 | Returns |
|
312 | 318 | ------- |
|
313 | 319 | session_id : int |
|
314 | 320 | Session ID number |
|
315 | 321 | start : datetime |
|
316 | 322 | Timestamp for the start of the session. |
|
317 | 323 | end : datetime |
|
318 | 324 | Timestamp for the end of the session, or None if IPython crashed. |
|
319 | 325 | num_cmds : int |
|
320 | 326 | Number of commands run, or None if IPython crashed. |
|
321 | 327 | remark : unicode |
|
322 | 328 | A manually set description. |
|
323 | 329 | """ |
|
324 | 330 | query = "SELECT * from sessions where session == ?" |
|
325 | 331 | return self.db.execute(query, (session,)).fetchone() |
|
326 | 332 | |
|
327 | 333 | @catch_corrupt_db |
|
328 | 334 | def get_last_session_id(self): |
|
329 | 335 | """Get the last session ID currently in the database. |
|
330 | 336 | |
|
331 | 337 | Within IPython, this should be the same as the value stored in |
|
332 | 338 | :attr:`HistoryManager.session_number`. |
|
333 | 339 | """ |
|
334 | 340 | for record in self.get_tail(n=1, include_latest=True): |
|
335 | 341 | return record[0] |
|
336 | 342 | |
|
337 | 343 | @catch_corrupt_db |
|
338 | 344 | def get_tail(self, n=10, raw=True, output=False, include_latest=False): |
|
339 | 345 | """Get the last n lines from the history database. |
|
340 | 346 | |
|
341 | 347 | Parameters |
|
342 | 348 | ---------- |
|
343 | 349 | n : int |
|
344 | 350 | The number of lines to get |
|
345 | 351 | raw, output : bool |
|
346 | 352 | See :meth:`get_range` |
|
347 | 353 | include_latest : bool |
|
348 | 354 | If False (default), n+1 lines are fetched, and the latest one |
|
349 | 355 | is discarded. This is intended to be used where the function |
|
350 | 356 | is called by a user command, which it should not return. |
|
351 | 357 | |
|
352 | 358 | Returns |
|
353 | 359 | ------- |
|
354 | 360 | Tuples as :meth:`get_range` |
|
355 | 361 | """ |
|
356 | 362 | self.writeout_cache() |
|
357 | 363 | if not include_latest: |
|
358 | 364 | n += 1 |
|
359 | 365 | cur = self._run_sql("ORDER BY session DESC, line DESC LIMIT ?", |
|
360 | 366 | (n,), raw=raw, output=output) |
|
361 | 367 | if not include_latest: |
|
362 | 368 | return reversed(list(cur)[1:]) |
|
363 | 369 | return reversed(list(cur)) |
|
364 | 370 | |
|
365 | 371 | @catch_corrupt_db |
|
366 | 372 | def search(self, pattern="*", raw=True, search_raw=True, |
|
367 | 373 | output=False, n=None, unique=False): |
|
368 | 374 | """Search the database using unix glob-style matching (wildcards |
|
369 | 375 | * and ?). |
|
370 | 376 | |
|
371 | 377 | Parameters |
|
372 | 378 | ---------- |
|
373 | 379 | pattern : str |
|
374 | 380 | The wildcarded pattern to match when searching |
|
375 | 381 | search_raw : bool |
|
376 | 382 | If True, search the raw input, otherwise, the parsed input |
|
377 | 383 | raw, output : bool |
|
378 | 384 | See :meth:`get_range` |
|
379 | 385 | n : None or int |
|
380 | 386 | If an integer is given, it defines the limit of |
|
381 | 387 | returned entries. |
|
382 | 388 | unique : bool |
|
383 | 389 | When it is true, return only unique entries. |
|
384 | 390 | |
|
385 | 391 | Returns |
|
386 | 392 | ------- |
|
387 | 393 | Tuples as :meth:`get_range` |
|
388 | 394 | """ |
|
389 | 395 | tosearch = "source_raw" if search_raw else "source" |
|
390 | 396 | if output: |
|
391 | 397 | tosearch = "history." + tosearch |
|
392 | 398 | self.writeout_cache() |
|
393 | 399 | sqlform = "WHERE %s GLOB ?" % tosearch |
|
394 | 400 | params = (pattern,) |
|
395 | 401 | if unique: |
|
396 | 402 | sqlform += ' GROUP BY {0}'.format(tosearch) |
|
397 | 403 | if n is not None: |
|
398 | 404 | sqlform += " ORDER BY session DESC, line DESC LIMIT ?" |
|
399 | 405 | params += (n,) |
|
400 | 406 | elif unique: |
|
401 | 407 | sqlform += " ORDER BY session, line" |
|
402 | 408 | cur = self._run_sql(sqlform, params, raw=raw, output=output, latest=unique) |
|
403 | 409 | if n is not None: |
|
404 | 410 | return reversed(list(cur)) |
|
405 | 411 | return cur |
|
406 | 412 | |
|
407 | 413 | @catch_corrupt_db |
|
408 | 414 | def get_range(self, session, start=1, stop=None, raw=True,output=False): |
|
409 | 415 | """Retrieve input by session. |
|
410 | 416 | |
|
411 | 417 | Parameters |
|
412 | 418 | ---------- |
|
413 | 419 | session : int |
|
414 | 420 | Session number to retrieve. |
|
415 | 421 | start : int |
|
416 | 422 | First line to retrieve. |
|
417 | 423 | stop : int |
|
418 | 424 | End of line range (excluded from output itself). If None, retrieve |
|
419 | 425 | to the end of the session. |
|
420 | 426 | raw : bool |
|
421 | 427 | If True, return untranslated input |
|
422 | 428 | output : bool |
|
423 | 429 | If True, attempt to include output. This will be 'real' Python |
|
424 | 430 | objects for the current session, or text reprs from previous |
|
425 | 431 | sessions if db_log_output was enabled at the time. Where no output |
|
426 | 432 | is found, None is used. |
|
427 | 433 | |
|
428 | 434 | Returns |
|
429 | 435 | ------- |
|
430 | 436 | entries |
|
431 | 437 | An iterator over the desired lines. Each line is a 3-tuple, either |
|
432 | 438 | (session, line, input) if output is False, or |
|
433 | 439 | (session, line, (input, output)) if output is True. |
|
434 | 440 | """ |
|
435 | 441 | if stop: |
|
436 | 442 | lineclause = "line >= ? AND line < ?" |
|
437 | 443 | params = (session, start, stop) |
|
438 | 444 | else: |
|
439 | 445 | lineclause = "line>=?" |
|
440 | 446 | params = (session, start) |
|
441 | 447 | |
|
442 | 448 | return self._run_sql("WHERE session==? AND %s" % lineclause, |
|
443 | 449 | params, raw=raw, output=output) |
|
444 | 450 | |
|
445 | 451 | def get_range_by_str(self, rangestr, raw=True, output=False): |
|
446 | 452 | """Get lines of history from a string of ranges, as used by magic |
|
447 | 453 | commands %hist, %save, %macro, etc. |
|
448 | 454 | |
|
449 | 455 | Parameters |
|
450 | 456 | ---------- |
|
451 | 457 | rangestr : str |
|
452 | 458 | A string specifying ranges, e.g. "5 ~2/1-4". If empty string is used, |
|
453 | 459 | this will return everything from current session's history. |
|
454 | 460 | |
|
455 | 461 | See the documentation of :func:`%history` for the full details. |
|
456 | 462 | |
|
457 | 463 | raw, output : bool |
|
458 | 464 | As :meth:`get_range` |
|
459 | 465 | |
|
460 | 466 | Returns |
|
461 | 467 | ------- |
|
462 | 468 | Tuples as :meth:`get_range` |
|
463 | 469 | """ |
|
464 | 470 | for sess, s, e in extract_hist_ranges(rangestr): |
|
465 | 471 | for line in self.get_range(sess, s, e, raw=raw, output=output): |
|
466 | 472 | yield line |
|
467 | 473 | |
|
468 | 474 | |
|
469 | 475 | class HistoryManager(HistoryAccessor): |
|
470 | 476 | """A class to organize all history-related functionality in one place. |
|
471 | 477 | """ |
|
472 | 478 | # Public interface |
|
473 | 479 | |
|
474 | 480 | # An instance of the IPython shell we are attached to |
|
475 | 481 | shell = Instance('IPython.core.interactiveshell.InteractiveShellABC', |
|
476 | 482 | allow_none=True) |
|
477 | 483 | # Lists to hold processed and raw history. These start with a blank entry |
|
478 | 484 | # so that we can index them starting from 1 |
|
479 | 485 | input_hist_parsed = List([""]) |
|
480 | 486 | input_hist_raw = List([""]) |
|
481 | 487 | # A list of directories visited during session |
|
482 | 488 | dir_hist = List() |
|
483 | 489 | @default('dir_hist') |
|
484 | 490 | def _dir_hist_default(self): |
|
485 | 491 | try: |
|
486 | 492 | return [Path.cwd()] |
|
487 | 493 | except OSError: |
|
488 | 494 | return [] |
|
489 | 495 | |
|
490 | 496 | # A dict of output history, keyed with ints from the shell's |
|
491 | 497 | # execution count. |
|
492 | 498 | output_hist = Dict() |
|
493 | 499 | # The text/plain repr of outputs. |
|
494 | 500 | output_hist_reprs = Dict() |
|
495 | 501 | |
|
496 | 502 | # The number of the current session in the history database |
|
497 | 503 | session_number = Integer() |
|
498 | 504 | |
|
499 | 505 | db_log_output = Bool(False, |
|
500 | 506 | help="Should the history database include output? (default: no)" |
|
501 | 507 | ).tag(config=True) |
|
502 | 508 | db_cache_size = Integer(0, |
|
503 | 509 | help="Write to database every x commands (higher values save disk access & power).\n" |
|
504 | 510 | "Values of 1 or less effectively disable caching." |
|
505 | 511 | ).tag(config=True) |
|
506 | 512 | # The input and output caches |
|
507 | 513 | db_input_cache = List() |
|
508 | 514 | db_output_cache = List() |
|
509 | 515 | |
|
510 | 516 | # History saving in separate thread |
|
511 | 517 | save_thread = Instance('IPython.core.history.HistorySavingThread', |
|
512 | 518 | allow_none=True) |
|
513 | 519 | save_flag = Instance(threading.Event, allow_none=True) |
|
514 | 520 | |
|
515 | 521 | # Private interface |
|
516 | 522 | # Variables used to store the three last inputs from the user. On each new |
|
517 | 523 | # history update, we populate the user's namespace with these, shifted as |
|
518 | 524 | # necessary. |
|
519 | 525 | _i00 = Unicode(u'') |
|
520 | 526 | _i = Unicode(u'') |
|
521 | 527 | _ii = Unicode(u'') |
|
522 | 528 | _iii = Unicode(u'') |
|
523 | 529 | |
|
524 | 530 | # A regex matching all forms of the exit command, so that we don't store |
|
525 | 531 | # them in the history (it's annoying to rewind the first entry and land on |
|
526 | 532 | # an exit call). |
|
527 | 533 | _exit_re = re.compile(r"(exit|quit)(\s*\(.*\))?$") |
|
528 | 534 | |
|
529 | 535 | def __init__(self, shell=None, config=None, **traits): |
|
530 | 536 | """Create a new history manager associated with a shell instance. |
|
531 | 537 | """ |
|
532 | 538 | # We need a pointer back to the shell for various tasks. |
|
533 | 539 | super(HistoryManager, self).__init__(shell=shell, config=config, |
|
534 | 540 | **traits) |
|
535 | 541 | self.save_flag = threading.Event() |
|
536 | 542 | self.db_input_cache_lock = threading.Lock() |
|
537 | 543 | self.db_output_cache_lock = threading.Lock() |
|
538 | 544 | |
|
539 | 545 | try: |
|
540 | 546 | self.new_session() |
|
541 | 547 | except sqlite3.OperationalError: |
|
542 | 548 | self.log.error("Failed to create history session in %s. History will not be saved.", |
|
543 | 549 | self.hist_file, exc_info=True) |
|
544 | 550 | self.hist_file = ':memory:' |
|
545 | 551 | |
|
546 | 552 | if self.enabled and self.hist_file != ':memory:': |
|
547 | 553 | self.save_thread = HistorySavingThread(self) |
|
548 | 554 | self.save_thread.start() |
|
549 | 555 | |
|
550 | 556 | def _get_hist_file_name(self, profile=None): |
|
551 | 557 | """Get default history file name based on the Shell's profile. |
|
552 | 558 | |
|
553 | 559 | The profile parameter is ignored, but must exist for compatibility with |
|
554 | 560 | the parent class.""" |
|
555 | 561 | profile_dir = self.shell.profile_dir.location |
|
556 | 562 | return Path(profile_dir) / "history.sqlite" |
|
557 | 563 | |
|
558 | 564 | @only_when_enabled |
|
559 | 565 | def new_session(self, conn=None): |
|
560 | 566 | """Get a new session number.""" |
|
561 | 567 | if conn is None: |
|
562 | 568 | conn = self.db |
|
563 | 569 | |
|
564 | 570 | with conn: |
|
565 | 571 | cur = conn.execute("""INSERT INTO sessions VALUES (NULL, ?, NULL, |
|
566 | 572 | NULL, "") """, (datetime.datetime.now(),)) |
|
567 | 573 | self.session_number = cur.lastrowid |
|
568 | 574 | |
|
569 | 575 | def end_session(self): |
|
570 | 576 | """Close the database session, filling in the end time and line count.""" |
|
571 | 577 | self.writeout_cache() |
|
572 | 578 | with self.db: |
|
573 | 579 | self.db.execute("""UPDATE sessions SET end=?, num_cmds=? WHERE |
|
574 | 580 | session==?""", (datetime.datetime.now(), |
|
575 | 581 | len(self.input_hist_parsed)-1, self.session_number)) |
|
576 | 582 | self.session_number = 0 |
|
577 | 583 | |
|
578 | 584 | def name_session(self, name): |
|
579 | 585 | """Give the current session a name in the history database.""" |
|
580 | 586 | with self.db: |
|
581 | 587 | self.db.execute("UPDATE sessions SET remark=? WHERE session==?", |
|
582 | 588 | (name, self.session_number)) |
|
583 | 589 | |
|
584 | 590 | def reset(self, new_session=True): |
|
585 | 591 | """Clear the session history, releasing all object references, and |
|
586 | 592 | optionally open a new session.""" |
|
587 | 593 | self.output_hist.clear() |
|
588 | 594 | # The directory history can't be completely empty |
|
589 | 595 | self.dir_hist[:] = [Path.cwd()] |
|
590 | 596 | |
|
591 | 597 | if new_session: |
|
592 | 598 | if self.session_number: |
|
593 | 599 | self.end_session() |
|
594 | 600 | self.input_hist_parsed[:] = [""] |
|
595 | 601 | self.input_hist_raw[:] = [""] |
|
596 | 602 | self.new_session() |
|
597 | 603 | |
|
598 | 604 | # ------------------------------ |
|
599 | 605 | # Methods for retrieving history |
|
600 | 606 | # ------------------------------ |
|
601 | 607 | def get_session_info(self, session=0): |
|
602 | 608 | """Get info about a session. |
|
603 | 609 | |
|
604 | 610 | Parameters |
|
605 | 611 | ---------- |
|
606 | 612 | session : int |
|
607 | 613 | Session number to retrieve. The current session is 0, and negative |
|
608 | 614 | numbers count back from current session, so -1 is the previous session. |
|
609 | 615 | |
|
610 | 616 | Returns |
|
611 | 617 | ------- |
|
612 | 618 | session_id : int |
|
613 | 619 | Session ID number |
|
614 | 620 | start : datetime |
|
615 | 621 | Timestamp for the start of the session. |
|
616 | 622 | end : datetime |
|
617 | 623 | Timestamp for the end of the session, or None if IPython crashed. |
|
618 | 624 | num_cmds : int |
|
619 | 625 | Number of commands run, or None if IPython crashed. |
|
620 | 626 | remark : unicode |
|
621 | 627 | A manually set description. |
|
622 | 628 | """ |
|
623 | 629 | if session <= 0: |
|
624 | 630 | session += self.session_number |
|
625 | 631 | |
|
626 | 632 | return super(HistoryManager, self).get_session_info(session=session) |
|
627 | 633 | |
|
628 | 634 | def _get_range_session(self, start=1, stop=None, raw=True, output=False): |
|
629 | 635 | """Get input and output history from the current session. Called by |
|
630 | 636 | get_range, and takes similar parameters.""" |
|
631 | 637 | input_hist = self.input_hist_raw if raw else self.input_hist_parsed |
|
632 | 638 | |
|
633 | 639 | n = len(input_hist) |
|
634 | 640 | if start < 0: |
|
635 | 641 | start += n |
|
636 | 642 | if not stop or (stop > n): |
|
637 | 643 | stop = n |
|
638 | 644 | elif stop < 0: |
|
639 | 645 | stop += n |
|
640 | 646 | |
|
641 | 647 | for i in range(start, stop): |
|
642 | 648 | if output: |
|
643 | 649 | line = (input_hist[i], self.output_hist_reprs.get(i)) |
|
644 | 650 | else: |
|
645 | 651 | line = input_hist[i] |
|
646 | 652 | yield (0, i, line) |
|
647 | 653 | |
|
648 | 654 | def get_range(self, session=0, start=1, stop=None, raw=True,output=False): |
|
649 | 655 | """Retrieve input by session. |
|
650 | 656 | |
|
651 | 657 | Parameters |
|
652 | 658 | ---------- |
|
653 | 659 | session : int |
|
654 | 660 | Session number to retrieve. The current session is 0, and negative |
|
655 | 661 | numbers count back from current session, so -1 is previous session. |
|
656 | 662 | start : int |
|
657 | 663 | First line to retrieve. |
|
658 | 664 | stop : int |
|
659 | 665 | End of line range (excluded from output itself). If None, retrieve |
|
660 | 666 | to the end of the session. |
|
661 | 667 | raw : bool |
|
662 | 668 | If True, return untranslated input |
|
663 | 669 | output : bool |
|
664 | 670 | If True, attempt to include output. This will be 'real' Python |
|
665 | 671 | objects for the current session, or text reprs from previous |
|
666 | 672 | sessions if db_log_output was enabled at the time. Where no output |
|
667 | 673 | is found, None is used. |
|
668 | 674 | |
|
669 | 675 | Returns |
|
670 | 676 | ------- |
|
671 | 677 | entries |
|
672 | 678 | An iterator over the desired lines. Each line is a 3-tuple, either |
|
673 | 679 | (session, line, input) if output is False, or |
|
674 | 680 | (session, line, (input, output)) if output is True. |
|
675 | 681 | """ |
|
676 | 682 | if session <= 0: |
|
677 | 683 | session += self.session_number |
|
678 | 684 | if session==self.session_number: # Current session |
|
679 | 685 | return self._get_range_session(start, stop, raw, output) |
|
680 | 686 | return super(HistoryManager, self).get_range(session, start, stop, raw, |
|
681 | 687 | output) |
|
682 | 688 | |
|
683 | 689 | ## ---------------------------- |
|
684 | 690 | ## Methods for storing history: |
|
685 | 691 | ## ---------------------------- |
|
686 | 692 | def store_inputs(self, line_num, source, source_raw=None): |
|
687 | 693 | """Store source and raw input in history and create input cache |
|
688 | 694 | variables ``_i*``. |
|
689 | 695 | |
|
690 | 696 | Parameters |
|
691 | 697 | ---------- |
|
692 | 698 | line_num : int |
|
693 | 699 | The prompt number of this input. |
|
694 | 700 | source : str |
|
695 | 701 | Python input. |
|
696 | 702 | source_raw : str, optional |
|
697 | 703 | If given, this is the raw input without any IPython transformations |
|
698 | 704 | applied to it. If not given, ``source`` is used. |
|
699 | 705 | """ |
|
700 | 706 | if source_raw is None: |
|
701 | 707 | source_raw = source |
|
702 | 708 | source = source.rstrip('\n') |
|
703 | 709 | source_raw = source_raw.rstrip('\n') |
|
704 | 710 | |
|
705 | 711 | # do not store exit/quit commands |
|
706 | 712 | if self._exit_re.match(source_raw.strip()): |
|
707 | 713 | return |
|
708 | 714 | |
|
709 | 715 | self.input_hist_parsed.append(source) |
|
710 | 716 | self.input_hist_raw.append(source_raw) |
|
711 | 717 | |
|
712 | 718 | with self.db_input_cache_lock: |
|
713 | 719 | self.db_input_cache.append((line_num, source, source_raw)) |
|
714 | 720 | # Trigger to flush cache and write to DB. |
|
715 | 721 | if len(self.db_input_cache) >= self.db_cache_size: |
|
716 | 722 | self.save_flag.set() |
|
717 | 723 | |
|
718 | 724 | # update the auto _i variables |
|
719 | 725 | self._iii = self._ii |
|
720 | 726 | self._ii = self._i |
|
721 | 727 | self._i = self._i00 |
|
722 | 728 | self._i00 = source_raw |
|
723 | 729 | |
|
724 | 730 | # hackish access to user namespace to create _i1,_i2... dynamically |
|
725 | 731 | new_i = '_i%s' % line_num |
|
726 | 732 | to_main = {'_i': self._i, |
|
727 | 733 | '_ii': self._ii, |
|
728 | 734 | '_iii': self._iii, |
|
729 | 735 | new_i : self._i00 } |
|
730 | 736 | |
|
731 | 737 | if self.shell is not None: |
|
732 | 738 | self.shell.push(to_main, interactive=False) |
|
733 | 739 | |
|
734 | 740 | def store_output(self, line_num): |
|
735 | 741 | """If database output logging is enabled, this saves all the |
|
736 | 742 | outputs from the indicated prompt number to the database. It's |
|
737 | 743 | called by run_cell after code has been executed. |
|
738 | 744 | |
|
739 | 745 | Parameters |
|
740 | 746 | ---------- |
|
741 | 747 | line_num : int |
|
742 | 748 | The line number from which to save outputs |
|
743 | 749 | """ |
|
744 | 750 | if (not self.db_log_output) or (line_num not in self.output_hist_reprs): |
|
745 | 751 | return |
|
746 | 752 | output = self.output_hist_reprs[line_num] |
|
747 | 753 | |
|
748 | 754 | with self.db_output_cache_lock: |
|
749 | 755 | self.db_output_cache.append((line_num, output)) |
|
750 | 756 | if self.db_cache_size <= 1: |
|
751 | 757 | self.save_flag.set() |
|
752 | 758 | |
|
753 | 759 | def _writeout_input_cache(self, conn): |
|
754 | 760 | with conn: |
|
755 | 761 | for line in self.db_input_cache: |
|
756 | 762 | conn.execute("INSERT INTO history VALUES (?, ?, ?, ?)", |
|
757 | 763 | (self.session_number,)+line) |
|
758 | 764 | |
|
759 | 765 | def _writeout_output_cache(self, conn): |
|
760 | 766 | with conn: |
|
761 | 767 | for line in self.db_output_cache: |
|
762 | 768 | conn.execute("INSERT INTO output_history VALUES (?, ?, ?)", |
|
763 | 769 | (self.session_number,)+line) |
|
764 | 770 | |
|
765 | 771 | @only_when_enabled |
|
766 | 772 | def writeout_cache(self, conn=None): |
|
767 | 773 | """Write any entries in the cache to the database.""" |
|
768 | 774 | if conn is None: |
|
769 | 775 | conn = self.db |
|
770 | 776 | |
|
771 | 777 | with self.db_input_cache_lock: |
|
772 | 778 | try: |
|
773 | 779 | self._writeout_input_cache(conn) |
|
774 | 780 | except sqlite3.IntegrityError: |
|
775 | 781 | self.new_session(conn) |
|
776 | 782 | print("ERROR! Session/line number was not unique in", |
|
777 | 783 | "database. History logging moved to new session", |
|
778 | 784 | self.session_number) |
|
779 | 785 | try: |
|
780 | 786 | # Try writing to the new session. If this fails, don't |
|
781 | 787 | # recurse |
|
782 | 788 | self._writeout_input_cache(conn) |
|
783 | 789 | except sqlite3.IntegrityError: |
|
784 | 790 | pass |
|
785 | 791 | finally: |
|
786 | 792 | self.db_input_cache = [] |
|
787 | 793 | |
|
788 | 794 | with self.db_output_cache_lock: |
|
789 | 795 | try: |
|
790 | 796 | self._writeout_output_cache(conn) |
|
791 | 797 | except sqlite3.IntegrityError: |
|
792 | 798 | print("!! Session/line number for output was not unique", |
|
793 | 799 | "in database. Output will not be stored.") |
|
794 | 800 | finally: |
|
795 | 801 | self.db_output_cache = [] |
|
796 | 802 | |
|
797 | 803 | |
|
798 | 804 | class HistorySavingThread(threading.Thread): |
|
799 | 805 | """This thread takes care of writing history to the database, so that |
|
800 | 806 | the UI isn't held up while that happens. |
|
801 | 807 | |
|
802 | 808 | It waits for the HistoryManager's save_flag to be set, then writes out |
|
803 | 809 | the history cache. The main thread is responsible for setting the flag when |
|
804 | 810 | the cache size reaches a defined threshold.""" |
|
805 | 811 | daemon = True |
|
806 | 812 | stop_now = False |
|
807 | 813 | enabled = True |
|
808 | 814 | def __init__(self, history_manager): |
|
809 | 815 | super(HistorySavingThread, self).__init__(name="IPythonHistorySavingThread") |
|
810 | 816 | self.history_manager = history_manager |
|
811 | 817 | self.enabled = history_manager.enabled |
|
812 | 818 | atexit.register(self.stop) |
|
813 | 819 | |
|
814 | 820 | @only_when_enabled |
|
815 | 821 | def run(self): |
|
816 | 822 | # We need a separate db connection per thread: |
|
817 | 823 | try: |
|
818 | 824 | self.db = sqlite3.connect( |
|
819 | 825 | str(self.history_manager.hist_file), |
|
820 | 826 | **self.history_manager.connection_options, |
|
821 | 827 | ) |
|
822 | 828 | while True: |
|
823 | 829 | self.history_manager.save_flag.wait() |
|
824 | 830 | if self.stop_now: |
|
825 | 831 | self.db.close() |
|
826 | 832 | return |
|
827 | 833 | self.history_manager.save_flag.clear() |
|
828 | 834 | self.history_manager.writeout_cache(self.db) |
|
829 | 835 | except Exception as e: |
|
830 | 836 | print(("The history saving thread hit an unexpected error (%s)." |
|
831 | 837 | "History will not be written to the database.") % repr(e)) |
|
832 | 838 | |
|
833 | 839 | def stop(self): |
|
834 | 840 | """This can be called from the main thread to safely stop this thread. |
|
835 | 841 | |
|
836 | 842 | Note that it does not attempt to write out remaining history before |
|
837 | 843 | exiting. That should be done by calling the HistoryManager's |
|
838 | 844 | end_session method.""" |
|
839 | 845 | self.stop_now = True |
|
840 | 846 | self.history_manager.save_flag.set() |
|
841 | 847 | self.join() |
|
842 | 848 | |
|
843 | 849 | |
|
844 | 850 | # To match, e.g. ~5/8-~2/3 |
|
845 | 851 | range_re = re.compile(r""" |
|
846 | 852 | ((?P<startsess>~?\d+)/)? |
|
847 | 853 | (?P<start>\d+)? |
|
848 | 854 | ((?P<sep>[\-:]) |
|
849 | 855 | ((?P<endsess>~?\d+)/)? |
|
850 | 856 | (?P<end>\d+))? |
|
851 | 857 | $""", re.VERBOSE) |
|
852 | 858 | |
|
853 | 859 | |
|
854 | 860 | def extract_hist_ranges(ranges_str): |
|
855 | 861 | """Turn a string of history ranges into 3-tuples of (session, start, stop). |
|
856 | 862 | |
|
857 | 863 | Empty string results in a `[(0, 1, None)]`, i.e. "everything from current |
|
858 | 864 | session". |
|
859 | 865 | |
|
860 | 866 | Examples |
|
861 | 867 | -------- |
|
862 | 868 | >>> list(extract_hist_ranges("~8/5-~7/4 2")) |
|
863 | 869 | [(-8, 5, None), (-7, 1, 5), (0, 2, 3)] |
|
864 | 870 | """ |
|
865 | 871 | if ranges_str == "": |
|
866 | 872 | yield (0, 1, None) # Everything from current session |
|
867 | 873 | return |
|
868 | 874 | |
|
869 | 875 | for range_str in ranges_str.split(): |
|
870 | 876 | rmatch = range_re.match(range_str) |
|
871 | 877 | if not rmatch: |
|
872 | 878 | continue |
|
873 | 879 | start = rmatch.group("start") |
|
874 | 880 | if start: |
|
875 | 881 | start = int(start) |
|
876 | 882 | end = rmatch.group("end") |
|
877 | 883 | # If no end specified, get (a, a + 1) |
|
878 | 884 | end = int(end) if end else start + 1 |
|
879 | 885 | else: # start not specified |
|
880 | 886 | if not rmatch.group('startsess'): # no startsess |
|
881 | 887 | continue |
|
882 | 888 | start = 1 |
|
883 | 889 | end = None # provide the entire session hist |
|
884 | 890 | |
|
885 | 891 | if rmatch.group("sep") == "-": # 1-3 == 1:4 --> [1, 2, 3] |
|
886 | 892 | end += 1 |
|
887 | 893 | startsess = rmatch.group("startsess") or "0" |
|
888 | 894 | endsess = rmatch.group("endsess") or startsess |
|
889 | 895 | startsess = int(startsess.replace("~","-")) |
|
890 | 896 | endsess = int(endsess.replace("~","-")) |
|
891 | 897 | assert endsess >= startsess, "start session must be earlier than end session" |
|
892 | 898 | |
|
893 | 899 | if endsess == startsess: |
|
894 | 900 | yield (startsess, start, end) |
|
895 | 901 | continue |
|
896 | 902 | # Multiple sessions in one range: |
|
897 | 903 | yield (startsess, start, None) |
|
898 | 904 | for sess in range(startsess+1, endsess): |
|
899 | 905 | yield (sess, 1, None) |
|
900 | 906 | yield (endsess, 1, end) |
|
901 | 907 | |
|
902 | 908 | |
|
903 | 909 | def _format_lineno(session, line): |
|
904 | 910 | """Helper function to format line numbers properly.""" |
|
905 | 911 | if session == 0: |
|
906 | 912 | return str(line) |
|
907 | 913 | return "%s#%s" % (session, line) |
General Comments 0
You need to be logged in to leave comments.
Login now