Fossil

Check-in [b5123d5154]
Login
Home Timeline Docs Branches Tickets Wiki DownloadMore...

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

Overview
Comment:adapt comments accordingly
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | improve_looks_like_binary
Files: files | file ages | folders
SHA1: b5123d51542a179578eeb754797a7223c062e342
User & Date: jan.nijtmans 2012-10-31 20:56:17.824
Context
2012-11-01
11:48
merge trunk <p>let looks_like_text() give different values for UTF-16 BE/LE. Not used yet. check-in: 348637dedf user: jan.nijtmans tags: improve_looks_like_binary
2012-10-31
20:56
adapt comments accordingly check-in: b5123d5154 user: jan.nijtmans tags: improve_looks_like_binary
20:49
Don't make it too complicated, too much risk to break other things. check-in: de5a2ef661 user: jan.nijtmans tags: improve_looks_like_binary
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/diff.c.
︙︙
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209

** values are:
**
**  (1) -- The content appears to consist entirely of text, with lines
**         delimited by line-feed characters; however, the encoding may
**         not be UTF-8.
**
**  (0) -- The content appears to be binary because it contains embedded
**         non-text characters - \0x0-\0x8, \0xe-\0x19, \0x1c-\0x1f, \uffff,
**         or \ufffe,\ufeff (except as BOM) - or an extremely long line.
**
** (-1) -- The content appears to consist entirely of text, with lines
**         delimited by carriage-return, line-feed pairs; however, the
**         encoding may not be UTF-8.
**
** (-2) -- The content appears to consist entirely of text, in the
**         UTF-16 (BE or LE) encoding.
*/
int looks_like_text(const Blob *pContent){
  unsigned char *z = (unsigned char *) blob_buffer(pContent);
  unsigned int n = blob_size(pContent);
  int j;
  unsigned char c;
  int result = 1;  /* Assume text with no CR/NL */

  /*
  **  Check individual lines.
  */
  if( n==0 ) return result;  /* Empty file -> text */
  c = *z;
  if( c==0 ) return 0;  /* \000 byte in a file -> binary */
  if ( (n&1)==0 ){ /* UTF-16 must have an even blob length */
    if ( (c==0xff) && (z[1]==0xfe) ){ /* UTF-16 LE BOM */
      result = -2;








<
|















<
|








177
178
179
180
181
182
183

184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199

200
201
202
203
204
205
206
207

** values are:
**
**  (1) -- The content appears to consist entirely of text, with lines
**         delimited by line-feed characters; however, the encoding may
**         not be UTF-8.
**
**  (0) -- The content appears to be binary because it contains embedded

**         NUL (\000) characters or an extremely long line.
**
** (-1) -- The content appears to consist entirely of text, with lines
**         delimited by carriage-return, line-feed pairs; however, the
**         encoding may not be UTF-8.
**
** (-2) -- The content appears to consist entirely of text, in the
**         UTF-16 (BE or LE) encoding.
*/
int looks_like_text(const Blob *pContent){
  unsigned char *z = (unsigned char *) blob_buffer(pContent);
  unsigned int n = blob_size(pContent);
  int j;
  unsigned char c;
  int result = 1;  /* Assume text with no CR/NL */


  /* Check individual lines.
  */
  if( n==0 ) return result;  /* Empty file -> text */
  c = *z;
  if( c==0 ) return 0;  /* \000 byte in a file -> binary */
  if ( (n&1)==0 ){ /* UTF-16 must have an even blob length */
    if ( (c==0xff) && (z[1]==0xfe) ){ /* UTF-16 LE BOM */
      result = -2;
︙︙
Changes to src/doc.c.
︙︙
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38


/*
** Try to guess the mimetype from content.
**
** If the content is pure text, return NULL.
**
** For image types, attempt to return an appropriate mimetype
** name like "image/gif" or "image/jpeg".  
**
** For any other binary type, return "unknown/unknown".
*/
const char *mimetype_from_content(Blob *pBlob){
  int i;
  int n;
  const unsigned char *x;








|








24
25
26
27
28
29
30
31
32
33
34
35
36
37
38


/*
** Try to guess the mimetype from content.
**
** If the content is pure text, return NULL.
**
** For image types, attempt to return an appropriate mimetype
** name like "image/gif" or "image/jpeg".
**
** For any other binary type, return "unknown/unknown".
*/
const char *mimetype_from_content(Blob *pBlob){
  int i;
  int n;
  const unsigned char *x;
︙︙
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95

const char *mimetype_from_name(const char *zName){
  const char *z;
  int i;
  int first, last;
  int len;
  char zSuffix[20];

  /* A table of mimetypes based on file suffixes. 
  ** Suffixes must be in sorted order so that we can do a binary
  ** search to find the mime-type
  */
  static const struct {
    const char *zSuffix;       /* The file suffix */
    int size;                  /* Length of the suffix */
    const char *zMimetype;     /* The corresponding mimetype */








|








81
82
83
84
85
86
87
88
89
90
91
92
93
94
95

const char *mimetype_from_name(const char *zName){
  const char *z;
  int i;
  int first, last;
  int len;
  char zSuffix[20];

  /* A table of mimetypes based on file suffixes.
  ** Suffixes must be in sorted order so that we can do a binary
  ** search to find the mime-type
  */
  static const struct {
    const char *zSuffix;       /* The file suffix */
    int size;                  /* Length of the suffix */
    const char *zMimetype;     /* The corresponding mimetype */
︙︙
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486

    if( content_get(rid, &filebody)==0 ){
      goto doc_not_found;
    }
    db_end_transaction(0);
  }

  /* The file is now contained in the filebody blob.  Deliver the
  ** file to the user 
  */
  zMime = P("mimetype");
  if( zMime==0 ){
    zMime = mimetype_from_name(zName);
  }
  Th_Store("doc_name", zName);
  Th_Store("doc_version", db_text(0, "SELECT '[' || substr(uuid,1,10) || ']'"








|








472
473
474
475
476
477
478
479
480
481
482
483
484
485
486

    if( content_get(rid, &filebody)==0 ){
      goto doc_not_found;
    }
    db_end_transaction(0);
  }

  /* The file is now contained in the filebody blob.  Deliver the
  ** file to the user
  */
  zMime = P("mimetype");
  if( zMime==0 ){
    zMime = mimetype_from_name(zName);
  }
  Th_Store("doc_name", zName);
  Th_Store("doc_version", db_text(0, "SELECT '[' || substr(uuid,1,10) || ']'"
︙︙
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593


doc_not_found:
  /* Jump here when unable to locate the document */
  db_end_transaction(0);
  style_header("Document Not Found");
  @ <p>No such document: %h(zName)</p>
  style_footer();
  return;  
}

/*
** The default logo.
*/
static const unsigned char aLogo[] = {
    71,  73,  70,  56,  55,  97,  62,   0,  71,   0, 244,   0,   0,  85, 
   129, 149,  95, 136, 155,  99, 139, 157, 106, 144, 162, 113, 150, 166, 
   116, 152, 168, 127, 160, 175, 138, 168, 182, 148, 176, 188, 159, 184, 
   195, 170, 192, 202, 180, 199, 208, 184, 202, 210, 191, 207, 215, 201, 
   215, 221, 212, 223, 228, 223, 231, 235, 226, 227, 226, 226, 234, 237, 
   233, 239, 241, 240, 244, 246, 244, 247, 248, 255, 255, 255,   0,   0, 
     0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0, 
     0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,  44,   0,   0, 
     0,   0,  62,   0,  71,   0,   0,   5, 255,  96, 100, 141, 100, 105, 
   158, 168,  37,  41, 132, 192, 164, 112,  44, 207, 102,  99,   0,  56, 
    16,  84, 116, 239, 199, 141,  65, 110, 232, 248,  25, 141, 193, 161, 
    82, 113, 108, 202,  32,  55, 229, 210,  73,  61,  41, 164,  88, 102, 
   181,  10,  41,  96, 179,  91, 106,  35, 240,   5, 135, 143, 137, 242, 
    87, 123, 246,  33, 190,  81, 108, 163, 237, 198,  14,  30, 113, 233, 
   131,  78, 115,  72,  11, 115,  87, 101,  19, 124,  51,  66,  74,   8, 
    19,  16,  67, 100,  74, 133,  50,  15, 101, 135,  56,  11,  74,   6, 
   143,  49, 126, 106,  56,   8, 145,  67,   9, 152,  48, 139, 155,   5, 
    22,  13,  74, 115, 161,  41, 147, 101,  13, 130,  57, 132, 170,  40, 
   167, 155,   0,  94,  57,   3, 178,  48, 183, 181,  57, 160, 186,  40, 
    19, 141, 189,   0,  69, 192,  40,  16, 195, 155, 185, 199,  41, 201, 
   189, 191, 205, 193, 188, 131, 210,  49, 175,  88, 209, 214,  38,  19, 
     3,  11,  19, 111, 127,  60, 219,  39,  55, 204,  19,  11,   6, 100, 
     5,  10, 227, 228,  37, 163,   0, 239, 117,  56, 238, 243,  49, 195, 
   177, 247,  48, 158,  56, 251,  50, 216, 254, 197,  56, 128, 107, 158, 
     2, 125, 171, 114,  92, 218, 246,  96,  66,   3,   4,  50, 134, 176, 
   145,   6,  97,  64, 144,  24,  19, 136, 108,  91, 177, 160,   0, 194, 
    19, 253,   0, 216, 107, 214, 224, 192, 129,   5,  16,  83, 255, 244, 
    43, 213, 195,  24, 159,  27, 169,  64, 230,  88, 208, 227, 129, 182, 
    54,   4,  89, 158,  24, 181, 163, 199,   1, 155,  52, 233,   8, 130, 
   176,  83,  24, 128, 137,  50,  18,  32,  48,  48, 114,  11, 173, 137, 
    19, 110,   4,  64, 105,   1, 194,  30, 140,  68,  15,  24,  24, 224, 
    50,  76,  70,   0,  11, 171,  54,  26, 160, 181, 194, 149, 148,  40, 
   174, 148, 122,  64, 180, 208, 161,  17, 207, 112, 164,   1, 128,  96, 
   148,  78,  18,  21, 194,  33, 229,  51, 247,  65, 133,  97,   5, 250, 
    69, 229, 100,  34, 220, 128, 166, 116, 190,  62,   8, 167, 195, 170, 
    47, 163,   0, 130,  90, 152,  11, 160, 173, 170,  27, 154,  26,  91, 
   232, 151, 171,  18,  14, 162, 253,  98, 170,  18,  70, 171,  64, 219, 
    10,  67, 136, 134, 187, 116,  75, 180,  46, 179, 174, 135,   4, 189, 
   229, 231,  78,  40,  10,  62, 226, 164, 172,  64, 240, 167, 170,  10, 
    18, 124, 188,  10, 107,  65, 193,  94,  11,  93, 171,  28, 248,  17, 
   239,  46, 140,  78,  97,  34,  25, 153,  36,  99,  65, 130,   7, 203, 
   183, 168,  51,  34, 136,  25, 140,  10,   6,  16,  28, 255, 145, 241, 
   230, 140,  10,  66, 178, 167, 112,  48, 192, 128, 129,   9,  31, 141, 
    84, 138,  63, 163, 162,   2, 203, 206, 240,  56,  55,  98, 192, 188, 
    15, 185,  50, 160,   6,   0, 125,  62,  33, 214, 195,  33,   5,  24, 
   184,  25, 231,  14, 201, 245, 144,  23, 126, 104, 228,   0, 145,   2, 
    13, 140, 244, 212,  17,  21,  20, 176, 159,  17,  95, 225, 160, 128, 
    16,   1,  32, 224, 142,  32, 227, 125,  87,  64,   0,  16,  54, 129, 
   205,   2, 141,  76,  53, 130, 103,  37, 166,  64, 144, 107,  78, 196, 
     5, 192,   0,  54,  50, 229,   9, 141,  49,  84, 194,  35,  12, 196, 
   153,  48, 192, 137,  57,  84,  24,   7,  87, 159, 249, 240, 215, 143, 
   105, 241, 118, 149,   9, 139,   4,  64, 203, 141,  35, 140, 129, 131, 
    16, 222, 125, 231, 128,   2, 238,  17, 152,  66,   3,   5,  56, 224, 
   159, 103,  16,  76,  25,  75,   5,  11, 164, 215,  96,   9,  14,  16, 
    36, 225,  15,  11,  40, 144, 192, 156,  41,  10, 178, 199,   3,  66, 
    64,  80, 193,   3, 124,  90,  48, 129, 129, 102, 177,  18, 192, 154, 
    49,  84, 240, 208,  92,  22, 149,  96,  39,   9,  31,  74,  17,  94, 
     3,   8, 177, 199,  72,  59,  85,  76,  25, 216,   8, 139, 194, 197, 
   138, 163,  69,  96, 115,   0, 147,  72,  72,  84,  28,  14,  79,  86, 
   233, 230,  23, 113,  26, 160, 128,   3,  10,  58, 129, 103,  14, 159, 
   214, 163, 146, 117, 238, 213, 154, 128, 151, 109,  84,  64, 217,  13, 
    27,  10, 228,  39,   2, 235, 164, 168,  74,   8,   0,  59, 
};

/*
** WEBPAGE: logo
**
** Return the logo image.  This image is available to anybody who can see
** the login page.  It is designed for use in the upper left-hand corner








|






|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|








511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593


doc_not_found:
  /* Jump here when unable to locate the document */
  db_end_transaction(0);
  style_header("Document Not Found");
  @ <p>No such document: %h(zName)</p>
  style_footer();
  return;
}

/*
** The default logo.
*/
static const unsigned char aLogo[] = {
    71,  73,  70,  56,  55,  97,  62,   0,  71,   0, 244,   0,   0,  85,
   129, 149,  95, 136, 155,  99, 139, 157, 106, 144, 162, 113, 150, 166,
   116, 152, 168, 127, 160, 175, 138, 168, 182, 148, 176, 188, 159, 184,
   195, 170, 192, 202, 180, 199, 208, 184, 202, 210, 191, 207, 215, 201,
   215, 221, 212, 223, 228, 223, 231, 235, 226, 227, 226, 226, 234, 237,
   233, 239, 241, 240, 244, 246, 244, 247, 248, 255, 255, 255,   0,   0,
     0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
     0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,  44,   0,   0,
     0,   0,  62,   0,  71,   0,   0,   5, 255,  96, 100, 141, 100, 105,
   158, 168,  37,  41, 132, 192, 164, 112,  44, 207, 102,  99,   0,  56,
    16,  84, 116, 239, 199, 141,  65, 110, 232, 248,  25, 141, 193, 161,
    82, 113, 108, 202,  32,  55, 229, 210,  73,  61,  41, 164,  88, 102,
   181,  10,  41,  96, 179,  91, 106,  35, 240,   5, 135, 143, 137, 242,
    87, 123, 246,  33, 190,  81, 108, 163, 237, 198,  14,  30, 113, 233,
   131,  78, 115,  72,  11, 115,  87, 101,  19, 124,  51,  66,  74,   8,
    19,  16,  67, 100,  74, 133,  50,  15, 101, 135,  56,  11,  74,   6,
   143,  49, 126, 106,  56,   8, 145,  67,   9, 152,  48, 139, 155,   5,
    22,  13,  74, 115, 161,  41, 147, 101,  13, 130,  57, 132, 170,  40,
   167, 155,   0,  94,  57,   3, 178,  48, 183, 181,  57, 160, 186,  40,
    19, 141, 189,   0,  69, 192,  40,  16, 195, 155, 185, 199,  41, 201,
   189, 191, 205, 193, 188, 131, 210,  49, 175,  88, 209, 214,  38,  19,
     3,  11,  19, 111, 127,  60, 219,  39,  55, 204,  19,  11,   6, 100,
     5,  10, 227, 228,  37, 163,   0, 239, 117,  56, 238, 243,  49, 195,
   177, 247,  48, 158,  56, 251,  50, 216, 254, 197,  56, 128, 107, 158,
     2, 125, 171, 114,  92, 218, 246,  96,  66,   3,   4,  50, 134, 176,
   145,   6,  97,  64, 144,  24,  19, 136, 108,  91, 177, 160,   0, 194,
    19, 253,   0, 216, 107, 214, 224, 192, 129,   5,  16,  83, 255, 244,
    43, 213, 195,  24, 159,  27, 169,  64, 230,  88, 208, 227, 129, 182,
    54,   4,  89, 158,  24, 181, 163, 199,   1, 155,  52, 233,   8, 130,
   176,  83,  24, 128, 137,  50,  18,  32,  48,  48, 114,  11, 173, 137,
    19, 110,   4,  64, 105,   1, 194,  30, 140,  68,  15,  24,  24, 224,
    50,  76,  70,   0,  11, 171,  54,  26, 160, 181, 194, 149, 148,  40,
   174, 148, 122,  64, 180, 208, 161,  17, 207, 112, 164,   1, 128,  96,
   148,  78,  18,  21, 194,  33, 229,  51, 247,  65, 133,  97,   5, 250,
    69, 229, 100,  34, 220, 128, 166, 116, 190,  62,   8, 167, 195, 170,
    47, 163,   0, 130,  90, 152,  11, 160, 173, 170,  27, 154,  26,  91,
   232, 151, 171,  18,  14, 162, 253,  98, 170,  18,  70, 171,  64, 219,
    10,  67, 136, 134, 187, 116,  75, 180,  46, 179, 174, 135,   4, 189,
   229, 231,  78,  40,  10,  62, 226, 164, 172,  64, 240, 167, 170,  10,
    18, 124, 188,  10, 107,  65, 193,  94,  11,  93, 171,  28, 248,  17,
   239,  46, 140,  78,  97,  34,  25, 153,  36,  99,  65, 130,   7, 203,
   183, 168,  51,  34, 136,  25, 140,  10,   6,  16,  28, 255, 145, 241,
   230, 140,  10,  66, 178, 167, 112,  48, 192, 128, 129,   9,  31, 141,
    84, 138,  63, 163, 162,   2, 203, 206, 240,  56,  55,  98, 192, 188,
    15, 185,  50, 160,   6,   0, 125,  62,  33, 214, 195,  33,   5,  24,
   184,  25, 231,  14, 201, 245, 144,  23, 126, 104, 228,   0, 145,   2,
    13, 140, 244, 212,  17,  21,  20, 176, 159,  17,  95, 225, 160, 128,
    16,   1,  32, 224, 142,  32, 227, 125,  87,  64,   0,  16,  54, 129,
   205,   2, 141,  76,  53, 130, 103,  37, 166,  64, 144, 107,  78, 196,
     5, 192,   0,  54,  50, 229,   9, 141,  49,  84, 194,  35,  12, 196,
   153,  48, 192, 137,  57,  84,  24,   7,  87, 159, 249, 240, 215, 143,
   105, 241, 118, 149,   9, 139,   4,  64, 203, 141,  35, 140, 129, 131,
    16, 222, 125, 231, 128,   2, 238,  17, 152,  66,   3,   5,  56, 224,
   159, 103,  16,  76,  25,  75,   5,  11, 164, 215,  96,   9,  14,  16,
    36, 225,  15,  11,  40, 144, 192, 156,  41,  10, 178, 199,   3,  66,
    64,  80, 193,   3, 124,  90,  48, 129, 129, 102, 177,  18, 192, 154,
    49,  84, 240, 208,  92,  22, 149,  96,  39,   9,  31,  74,  17,  94,
     3,   8, 177, 199,  72,  59,  85,  76,  25, 216,   8, 139, 194, 197,
   138, 163,  69,  96, 115,   0, 147,  72,  72,  84,  28,  14,  79,  86,
   233, 230,  23, 113,  26, 160, 128,   3,  10,  58, 129, 103,  14, 159,
   214, 163, 146, 117, 238, 213, 154, 128, 151, 109,  84,  64, 217,  13,
    27,  10, 228,  39,   2, 235, 164, 168,  74,   8,   0,  59,
};

/*
** WEBPAGE: logo
**
** Return the logo image.  This image is available to anybody who can see
** the login page.  It is designed for use in the upper left-hand corner
︙︙
This page was generated in about 0.026s by Fossil 2.26 [1205ec86cb] 2025-04-30 16:57:32