Mercurial Repositories > eric / file comparison
comparison: Utilities/__init__.py
Utilities/__init__.py
- changeset 6099
- a7fecbc392d7
- parent 6080
- 436ac20f7639
- child 6105
- cbd34d558bd9
equal
deleted
inserted
replaced
| 6098:a1d10c6ce103 | 6099:a7fecbc392d7 |
|---|---|
| 297 return str(text, "utf-8", "ignore"), 'utf-8-ignore' | 297 return str(text, "utf-8", "ignore"), 'utf-8-ignore' |
| 298 else: | 298 else: |
| 299 return decode(text) | 299 return decode(text) |
| 300 | 300 |
| 301 | 301 |
| 302 def writeEncodedFile(filename, text, orig_coding): | 302 def writeEncodedFile(filename, text, origEncoding, forcedEncoding=""): |
| 303 """ | 303 """ |
| 304 Function to write a file with properly encoded text. | 304 Function to write a file with properly encoded text. |
| 305 | 305 |
| 306 @param filename name of the file to read (string) | 306 @param filename name of the file to read |
| 307 @param text text to be written (string) | 307 @type str |
| 308 @param orig_coding type of the original encoding (string) | 308 @param text text to be written |
| 309 @return encoding used for writing the file (string) | 309 @type str |
| 310 """ | 310 @param origEncoding type of the original encoding |
| 311 etext, encoding = encode(text, orig_coding) | 311 @type str |
| 312 @param forcedEncoding encoding to be used for writing, if no coding | |
| 313 line is present | |
| 314 @type str | |
| 315 @return encoding used for writing the file | |
| 316 @rtype str | |
| 317 """ | |
| 318 etext, encoding = encode(text, origEncoding, forcedEncoding=forcedEncoding) | |
| 312 | 319 |
| 313 f = open(filename, "wb") | 320 f = open(filename, "wb") |
| 314 f.write(etext) | 321 f.write(etext) |
| 315 f.close() | 322 f.close() |
| 316 | 323 |
| 317 return encoding | 324 return encoding |
| 318 | 325 |
| 319 | 326 |
| 320 def encode(text, orig_coding): | 327 def encode(text, origEncoding, forcedEncoding=""): |
| 321 """ | 328 """ |
| 322 Function to encode text into a byte text. | 329 Function to encode text into a byte text. |
| 323 | 330 |
| 324 @param text text to be encoded (string) | 331 @param text text to be encoded |
| 325 @param orig_coding type of the original encoding (string) | 332 @type str |
| 326 @return tuple of encoded text and encoding used (bytes, string) | 333 @param origEncoding type of the original encoding |
| 334 @type str | |
| 335 @param forcedEncoding encoding to be used for writing, if no coding line | |
| 336 is present | |
| 337 @type str | |
| 338 @return tuple of encoded text and encoding used | |
| 339 @rtype tuple of (bytes, str) | |
| 327 @exception CodingError raised to indicate an invalid encoding | 340 @exception CodingError raised to indicate an invalid encoding |
| 328 """ | 341 """ |
| 329 encoding = None | 342 encoding = None |
| 330 if orig_coding == 'utf-8-bom': | 343 if origEncoding == 'utf-8-bom': |
| 331 etext, encoding = BOM_UTF8 + text.encode("utf-8"), 'utf-8-bom' | 344 etext, encoding = BOM_UTF8 + text.encode("utf-8"), 'utf-8-bom' |
| 332 else: | 345 else: |
| 333 # Try declared coding spec | 346 # Try declared coding spec |
| 334 coding = get_coding(text) | 347 coding = get_coding(text) |
| 335 if coding: | 348 if coding: |
| 337 etext, encoding = text.encode(coding), coding | 350 etext, encoding = text.encode(coding), coding |
| 338 except (UnicodeError, LookupError): | 351 except (UnicodeError, LookupError): |
| 339 # Error: Declared encoding is incorrect | 352 # Error: Declared encoding is incorrect |
| 340 raise CodingError(coding) | 353 raise CodingError(coding) |
| 341 else: | 354 else: |
| 342 if orig_coding and orig_coding.endswith( | 355 if forcedEncoding: |
| 343 ('-selected', '-default', '-guessed', '-ignore')): | |
| 344 coding = orig_coding\ | |
| 345 .replace("-selected", "")\ | |
| 346 .replace("-default", "")\ | |
| 347 .replace("-guessed", "")\ | |
| 348 .replace("-ignore", "") | |
| 349 try: | 356 try: |
| 350 etext, encoding = text.encode(coding), coding | 357 etext, encoding = ( |
| 358 text.encode(forcedEncoding), forcedEncoding) | |
| 351 except (UnicodeError, LookupError): | 359 except (UnicodeError, LookupError): |
| 360 # Error: Forced encoding is incorrect, ignore it | |
| 352 pass | 361 pass |
| 353 | 362 |
| 354 if encoding is None: | 363 if encoding is None: |
| 355 # Try configured default | 364 # Try the original encoding |
| 356 try: | 365 if origEncoding and origEncoding.endswith( |
| 357 codec = Preferences.getEditor("DefaultEncoding") | 366 ('-selected', '-default', '-guessed', '-ignore')): |
| 358 etext, encoding = text.encode(codec), codec | 367 coding = origEncoding\ |
| 359 except (UnicodeError, LookupError): | 368 .replace("-selected", "")\ |
| 360 pass | 369 .replace("-default", "")\ |
| 370 .replace("-guessed", "")\ | |
| 371 .replace("-ignore", "") | |
| 372 try: | |
| 373 etext, encoding = text.encode(coding), coding | |
| 374 except (UnicodeError, LookupError): | |
| 375 pass | |
| 361 | 376 |
| 362 if encoding is None: | 377 if encoding is None: |
| 363 # Try saving as ASCII | 378 # Try configured default |
| 364 try: | 379 try: |
| 365 etext, encoding = text.encode('ascii'), 'ascii' | 380 codec = Preferences.getEditor("DefaultEncoding") |
| 366 except UnicodeError: | 381 etext, encoding = text.encode(codec), codec |
| 382 except (UnicodeError, LookupError): | |
| 367 pass | 383 pass |
| 368 | 384 |
| 369 if encoding is None: | 385 if encoding is None: |
| 370 # Save as UTF-8 without BOM | 386 # Try saving as ASCII |
| 371 etext, encoding = text.encode('utf-8'), 'utf-8' | 387 try: |
| 388 etext, encoding = text.encode('ascii'), 'ascii' | |
| 389 except UnicodeError: | |
| 390 pass | |
| 391 | |
| 392 if encoding is None: | |
| 393 # Save as UTF-8 without BOM | |
| 394 etext, encoding = text.encode('utf-8'), 'utf-8' | |
| 372 | 395 |
| 373 return etext, encoding | 396 return etext, encoding |
| 374 | 397 |
| 375 | 398 |
| 376 def decodeString(text): | 399 def decodeString(text): |
