Changes On Branch looks-like-utf
Not logged in
Home Timeline DownloadDocumentationBranches Tags Tickets Login
Hide Diff Patch Unified Diff

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Changes In Branch looks-like-utf Excluding Merge-Ins

This is equivalent to a diff from eb3c9b34df to 468f134659

2013-04-08
02:10
Enhancements to the "bisect" command: Add "bisect log" and "bisect undo". The "bisect status" command is an alias for "bisect vlist". Show the adjacent good and bad versions on the final step of the bisect. check-in: 41c7ac29d7 user: drh tags: trunk
2013-04-04
11:35
merge trunk check-in: d8bc29f346 user: jan.nijtmans tags: improve_commit_warning
06:53
Simplyfy/speed-up use of LOOK_??? flags. Rename LOOK_CR/LF to LOOK_ANY_CR/LF. Closed-Leaf check-in: 468f134659 user: jan.nijtmans tags: looks-like-utf
06:43
copy/paste error in comment check-in: eb3c9b34df user: jan.nijtmans tags: trunk
2013-04-03
12:14
Restore the original UTF test numbering. check-in: 00f9c9e83a user: mistachkin tags: trunk

Changes to src/checkin.c.

︙︙
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951

  if( allOk ) return 0;
  fUnicode = could_be_utf16(p, &bReverse);
  if( fUnicode ){
    lookFlags = looks_like_utf16(p, bReverse, LOOK_NUL);
  }else{
    lookFlags = looks_like_utf8(p, LOOK_NUL);
  }
  fHasAnyCr = (lookFlags & LOOK_CR);
  fBinary = (lookFlags & LOOK_BINARY);
  fHasLoneCrOnly = ((lookFlags & LOOK_EOL) == LOOK_LONE_CR);
  fHasCrLfOnly = ((lookFlags & LOOK_EOL) == LOOK_CRLF);
  if( fUnicode || fHasAnyCr || fBinary ){
    const char *zWarning;
    const char *zDisable;
    const char *zConvert = "c=convert/";








|








937
938
939
940
941
942
943
944
945
946
947
948
949
950
951

  if( allOk ) return 0;
  fUnicode = could_be_utf16(p, &bReverse);
  if( fUnicode ){
    lookFlags = looks_like_utf16(p, bReverse, LOOK_NUL);
  }else{
    lookFlags = looks_like_utf8(p, LOOK_NUL);
  }
  fHasAnyCr = (lookFlags & LOOK_ANY_CR);
  fBinary = (lookFlags & LOOK_BINARY);
  fHasLoneCrOnly = ((lookFlags & LOOK_EOL) == LOOK_LONE_CR);
  fHasCrLfOnly = ((lookFlags & LOOK_EOL) == LOOK_CRLF);
  if( fUnicode || fHasAnyCr || fBinary ){
    const char *zWarning;
    const char *zDisable;
    const char *zConvert = "c=convert/";
︙︙

Changes to src/diff.c.

︙︙
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84


85
86
87
88
89
90
91
92


/*
** Output flags for the looks_like_utf8() and looks_like_utf16() routines used
** to convey status information about the blob content.
*/
#define LOOK_NONE    ((int)0x00000000) /* Nothing special was found. */
#define LOOK_NUL     ((int)0x00000001) /* One or more NUL chars were found. */
#define LOOK_CR      ((int)0x00000002) /* One or more CR chars were found. */
#define LOOK_LONE_CR ((int)0x00000004) /* An unpaired CR char was found. */
#define LOOK_LF      ((int)0x00000008) /* One or more LF chars were found. */
#define LOOK_LONE_LF ((int)0x00000010) /* An unpaired LF char was found. */
#define LOOK_CRLF    ((int)0x00000020) /* One or more CR/LF pairs were found. */
#define LOOK_LONG    ((int)0x00000040) /* An over length line was found. */
#define LOOK_ODD     ((int)0x00000080) /* An odd number of bytes was found. */
#define LOOK_SHORT   ((int)0x00000100) /* Unable to perform full check. */
#define LOOK_INVALID ((int)0x00000200) /* Invalid sequence was found. */
#define LOOK_BINARY  (LOOK_NUL | LOOK_LONG | LOOK_SHORT) /* May be binary. */


#define LOOK_EOL     (LOOK_LONE_CR | LOOK_LONE_LF | LOOK_CRLF) /* Line seps. */
#endif /* INTERFACE */

/*
** Maximum length of a line in a text file, in bytes.  (2**13 = 8192 bytes)
*/
#define LENGTH_MASK_SZ  13
#define LENGTH_MASK     ((1<<LENGTH_MASK_SZ)-1)








<

<







>
>
|








68
69
70
71
72
73
74

75

76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92


/*
** Output flags for the looks_like_utf8() and looks_like_utf16() routines used
** to convey status information about the blob content.
*/
#define LOOK_NONE    ((int)0x00000000) /* Nothing special was found. */
#define LOOK_NUL     ((int)0x00000001) /* One or more NUL chars were found. */

#define LOOK_LONE_CR ((int)0x00000004) /* An unpaired CR char was found. */

#define LOOK_LONE_LF ((int)0x00000010) /* An unpaired LF char was found. */
#define LOOK_CRLF    ((int)0x00000020) /* One or more CR/LF pairs were found. */
#define LOOK_LONG    ((int)0x00000040) /* An over length line was found. */
#define LOOK_ODD     ((int)0x00000080) /* An odd number of bytes was found. */
#define LOOK_SHORT   ((int)0x00000100) /* Unable to perform full check. */
#define LOOK_INVALID ((int)0x00000200) /* Invalid sequence was found. */
#define LOOK_BINARY  (LOOK_NUL | LOOK_LONG | LOOK_SHORT) /* May be binary. */
#define LOOK_ANY_CR  (LOOK_LONE_CR | LOOK_CRLF) /* One or more CR chars were found. */
#define LOOK_ANY_LF  (LOOK_LONE_LF | LOOK_CRLF) /* One or more LF chars were found. */
#define LOOK_EOL     (LOOK_ANY_CR | LOOK_LONE_LF) /* Line seps. */
#endif /* INTERFACE */

/*
** Maximum length of a line in a text file, in bytes.  (2**13 = 8192 bytes)
*/
#define LENGTH_MASK_SZ  13
#define LENGTH_MASK     ((1<<LENGTH_MASK_SZ)-1)
︙︙
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282

  int j, c, flags = LOOK_NONE;  /* Assume UTF-8 text, prove otherwise */

  if( n==0 ) return flags;  /* Empty file -> text */
  c = *z;
  if( c==0 ){
    flags |= LOOK_NUL;  /* NUL character in a file -> binary */
  }else if( c=='\r' ){
    flags |= LOOK_CR;
    if( n<=1 || z[1]!='\n' ){
      flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
    }
  }
  j = (c!='\n');
  if( !j ) flags |= (LOOK_LF | LOOK_LONE_LF);  /* Found LF as first char */
  while( !(flags&stopFlags) && --n>0 ){
    int c2 = c;
    c = *++z; ++j;
    if( c==0 ){
      flags |= LOOK_NUL;  /* NUL character in a file -> binary */
    }else if( c=='\n' ){
      flags |= LOOK_LF;
      if( c2=='\r' ){
        flags |= (LOOK_CR | LOOK_CRLF);  /* Found LF preceded by CR */
      }else{
        flags |= LOOK_LONE_LF;
      }
      if( j>LENGTH_MASK ){
        flags |= LOOK_LONG;  /* Very long line -> binary */
      }
      j = 0;
    }else if( c=='\r' ){
      flags |= LOOK_CR;
      if( n<=1 || z[1]!='\n' ){
        flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
      }
    }
  }
  if( n ){
    flags |= LOOK_SHORT;  /* Not the whole blob is examined */








<





|






<

|








<








244
245
246
247
248
249
250

251
252
253
254
255
256
257
258
259
260
261
262

263
264
265
266
267
268
269
270
271
272

273
274
275
276
277
278
279

  int j, c, flags = LOOK_NONE;  /* Assume UTF-8 text, prove otherwise */

  if( n==0 ) return flags;  /* Empty file -> text */
  c = *z;
  if( c==0 ){
    flags |= LOOK_NUL;  /* NUL character in a file -> binary */
  }else if( c=='\r' ){

    if( n<=1 || z[1]!='\n' ){
      flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
    }
  }
  j = (c!='\n');
  if( !j ) flags |= LOOK_LONE_LF;  /* Found LF as first char */
  while( !(flags&stopFlags) && --n>0 ){
    int c2 = c;
    c = *++z; ++j;
    if( c==0 ){
      flags |= LOOK_NUL;  /* NUL character in a file -> binary */
    }else if( c=='\n' ){

      if( c2=='\r' ){
        flags |= LOOK_CRLF;  /* Found LF preceded by CR */
      }else{
        flags |= LOOK_LONE_LF;
      }
      if( j>LENGTH_MASK ){
        flags |= LOOK_LONG;  /* Very long line -> binary */
      }
      j = 0;
    }else if( c=='\r' ){

      if( n<=1 || z[1]!='\n' ){
        flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
      }
    }
  }
  if( n ){
    flags |= LOOK_SHORT;  /* Not the whole blob is examined */
︙︙
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402

  c = *z;
  if( bReverse ){
    c = UTF16_SWAP(c);
  }
  if( c==0 ){
    flags |= LOOK_NUL;  /* NUL character in a file -> binary */
  }else if( c=='\r' ){
    flags |= LOOK_CR;
    if( n<=sizeof(WCHAR_T) || UTF16_SWAP_IF(bReverse, z[1])!='\n' ){
      flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
    }
  }
  j = (c!='\n');
  if( !j ) flags |= (LOOK_LF | LOOK_LONE_LF);  /* Found LF as first char */
  while( 1 ){
    int c2 = c;
    n -= sizeof(WCHAR_T);
    if( (flags&stopFlags) || n<sizeof(WCHAR_T) ) break;
    c = *++z;
    if( bReverse ){
      c = UTF16_SWAP(c);
    }
    ++j;
    if( c==0 ){
      flags |= LOOK_NUL;  /* NUL character in a file -> binary */
    }else if( c=='\n' ){
      flags |= LOOK_LF;
      if( c2=='\r' ){
        flags |= (LOOK_CR | LOOK_CRLF);  /* Found LF preceded by CR */
      }else{
        flags |= LOOK_LONE_LF;
      }
      if( j>UTF16_LENGTH_MASK ){
        flags |= LOOK_LONG;  /* Very long line -> binary */
      }
      j = 0;
    }else if( c=='\r' ){
      flags |= LOOK_CR;
      if( n<=sizeof(WCHAR_T) || UTF16_SWAP_IF(bReverse, z[1])!='\n' ){
        flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
      }
    }
  }
  if( n ){
    flags |= LOOK_SHORT;  /* Not the whole blob is examined */








<





|












<

|








<








355
356
357
358
359
360
361

362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379

380
381
382
383
384
385
386
387
388
389

390
391
392
393
394
395
396

  c = *z;
  if( bReverse ){
    c = UTF16_SWAP(c);
  }
  if( c==0 ){
    flags |= LOOK_NUL;  /* NUL character in a file -> binary */
  }else if( c=='\r' ){

    if( n<=sizeof(WCHAR_T) || UTF16_SWAP_IF(bReverse, z[1])!='\n' ){
      flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
    }
  }
  j = (c!='\n');
  if( !j ) flags |= LOOK_LONE_LF;  /* Found LF as first char */
  while( 1 ){
    int c2 = c;
    n -= sizeof(WCHAR_T);
    if( (flags&stopFlags) || n<sizeof(WCHAR_T) ) break;
    c = *++z;
    if( bReverse ){
      c = UTF16_SWAP(c);
    }
    ++j;
    if( c==0 ){
      flags |= LOOK_NUL;  /* NUL character in a file -> binary */
    }else if( c=='\n' ){

      if( c2=='\r' ){
        flags |= LOOK_CRLF;  /* Found LF preceded by CR */
      }else{
        flags |= LOOK_LONE_LF;
      }
      if( j>UTF16_LENGTH_MASK ){
        flags |= LOOK_LONG;  /* Very long line -> binary */
      }
      j = 0;
    }else if( c=='\r' ){

      if( n<=sizeof(WCHAR_T) || UTF16_SWAP_IF(bReverse, z[1])!='\n' ){
        flags |= LOOK_LONE_CR;  /* More chars, next char is not LF */
      }
    }
  }
  if( n ){
    flags |= LOOK_SHORT;  /* Not the whole blob is examined */
︙︙
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575

  fossil_print("File \"%s\" has %d bytes.\n",g.argv[2],blob_size(&blob));
  fossil_print("Starts with UTF-8 BOM: %s\n",fUtf8?"yes":"no");
  fossil_print("Starts with UTF-16 BOM: %s\n",
               fUtf16?(bRevUtf16?"reversed":"yes"):"no");
  fossil_print("Looks like UTF-%s: %s\n",fUnicode?"16":"8",
               (lookFlags&LOOK_BINARY)?"no":"yes");
  fossil_print("Has flag LOOK_NUL: %s\n",(lookFlags&LOOK_NUL)?"yes":"no");
  fossil_print("Has flag LOOK_CR: %s\n",(lookFlags&LOOK_CR)?"yes":"no");
  fossil_print("Has flag LOOK_LONE_CR: %s\n",
               (lookFlags&LOOK_LONE_CR)?"yes":"no");
  fossil_print("Has flag LOOK_LF: %s\n",(lookFlags&LOOK_LF)?"yes":"no");
  fossil_print("Has flag LOOK_LONE_LF: %s\n",
               (lookFlags&LOOK_LONE_LF)?"yes":"no");
  fossil_print("Has flag LOOK_CRLF: %s\n",(lookFlags&LOOK_CRLF)?"yes":"no");
  fossil_print("Has flag LOOK_LONG: %s\n",(lookFlags&LOOK_LONG)?"yes":"no");
  fossil_print("Has flag LOOK_INVALID: %s\n",
               (lookFlags&LOOK_INVALID)?"yes":"no");
  fossil_print("Has flag LOOK_ODD: %s\n",(lookFlags&LOOK_ODD)?"yes":"no");
  fossil_print("Has flag LOOK_SHORT: %s\n",(lookFlags&LOOK_SHORT)?"yes":"no");
  blob_reset(&blob);
}








|


|











2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569

  fossil_print("File \"%s\" has %d bytes.\n",g.argv[2],blob_size(&blob));
  fossil_print("Starts with UTF-8 BOM: %s\n",fUtf8?"yes":"no");
  fossil_print("Starts with UTF-16 BOM: %s\n",
               fUtf16?(bRevUtf16?"reversed":"yes"):"no");
  fossil_print("Looks like UTF-%s: %s\n",fUnicode?"16":"8",
               (lookFlags&LOOK_BINARY)?"no":"yes");
  fossil_print("Has flag LOOK_NUL: %s\n",(lookFlags&LOOK_NUL)?"yes":"no");
  fossil_print("Has flag LOOK_CR: %s\n",(lookFlags&LOOK_ANY_CR)?"yes":"no");
  fossil_print("Has flag LOOK_LONE_CR: %s\n",
               (lookFlags&LOOK_LONE_CR)?"yes":"no");
  fossil_print("Has flag LOOK_LF: %s\n",(lookFlags&LOOK_ANY_LF)?"yes":"no");
  fossil_print("Has flag LOOK_LONE_LF: %s\n",
               (lookFlags&LOOK_LONE_LF)?"yes":"no");
  fossil_print("Has flag LOOK_CRLF: %s\n",(lookFlags&LOOK_CRLF)?"yes":"no");
  fossil_print("Has flag LOOK_LONG: %s\n",(lookFlags&LOOK_LONG)?"yes":"no");
  fossil_print("Has flag LOOK_INVALID: %s\n",
               (lookFlags&LOOK_INVALID)?"yes":"no");
  fossil_print("Has flag LOOK_ODD: %s\n",(lookFlags&LOOK_ODD)?"yes":"no");
  fossil_print("Has flag LOOK_SHORT: %s\n",(lookFlags&LOOK_SHORT)?"yes":"no");
  blob_reset(&blob);
}

This page was generated in about 0.033s by Fossil version [66ee0beb9b] 2023-05-31 15:26:08