Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Overview
Comment: | Add the ability to display content and diffs for UTF16 text files in the web interface. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA1: |
5a66b6e7854f985a64324f74ce3a2933 |
User & Date: | drh 2014-01-14 12:44:59 |
References
2014-01-15
| ||
21:41 | Since [5a66b6e785] conversions from Unicode (actually: UTF-16) to UTF-8 are possible on UNIX too ... (check-in: d0d7ca17 user: jan.nijtmans tags: trunk) | |
Context
2014-01-14
| ||
13:39 | Handle utf16 text pages in the /doc webpage. ... (check-in: 1c5b51e6 user: drh tags: trunk) | |
12:44 | Add the ability to display content and diffs for UTF16 text files in the web interface. ... (check-in: 5a66b6e7 user: drh tags: trunk) | |
09:48 | Enable use of the TH1_DELETE_INTERP environment variable to delete the TH1 interp on exit. ... (check-in: e0f22dda user: mistachkin tags: trunk) | |
Changes
Changes to src/blob.c.
︙ | ︙ | |||
221 222 223 224 225 226 227 228 229 230 231 232 233 234 | /* ** Initialize a blob to a nul-terminated string. ** Any prior data in the blob is discarded. */ void blob_set(Blob *pBlob, const char *zStr){ blob_init(pBlob, zStr, -1); } /* ** Initialize a blob to an empty string. */ void blob_zero(Blob *pBlob){ static const char zEmpty[] = ""; assert_blob_is_reset(pBlob); | > > > > > > > > > | 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | /* ** Initialize a blob to a nul-terminated string. ** Any prior data in the blob is discarded. */ void blob_set(Blob *pBlob, const char *zStr){ blob_init(pBlob, zStr, -1); } /* ** Initialize a blob to a nul-terminated string obtained from fossil_malloc(). ** The blob will take responsibility for freeing the string. */ void blob_set_dynamic(Blob *pBlob, char *zStr){ blob_init(pBlob, zStr, -1); pBlob->xRealloc = blobReallocMalloc; } /* ** Initialize a blob to an empty string. */ void blob_zero(Blob *pBlob){ static const char zEmpty[] = ""; assert_blob_is_reset(pBlob); |
︙ | ︙ | |||
1093 1094 1095 1096 1097 1098 1099 | ** is either no BOM at all or an (le/be) UTF-16 BOM, a conversion to UTF-8 is ** done. If useMbcs is false and there is no BOM, the input string is assumed ** to be UTF-8 already, so no conversion is done. */ void blob_to_utf8_no_bom(Blob *pBlob, int useMbcs){ char *zUtf8; int bomSize = 0; | < < < < | < < | 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 | ** is either no BOM at all or an (le/be) UTF-16 BOM, a conversion to UTF-8 is ** done. If useMbcs is false and there is no BOM, the input string is assumed ** to be UTF-8 already, so no conversion is done. */ void blob_to_utf8_no_bom(Blob *pBlob, int useMbcs){ char *zUtf8; int bomSize = 0; int bomReverse = 0; if( starts_with_utf8_bom(pBlob, &bomSize) ){ struct Blob temp; zUtf8 = blob_str(pBlob) + bomSize; blob_zero(&temp); blob_append(&temp, zUtf8, -1); blob_swap(pBlob, &temp); blob_reset(&temp); }else if( starts_with_utf16_bom(pBlob, &bomSize, &bomReverse) ){ zUtf8 = blob_buffer(pBlob); if( bomReverse ){ /* Found BOM, but with reversed bytes */ unsigned int i = blob_size(pBlob); while( i>0 ){ /* swap bytes of unicode representation */ char zTemp = zUtf8[--i]; zUtf8[i] = zUtf8[i-1]; zUtf8[--i] = zTemp; } } /* Make sure the blob contains two terminating 0-bytes */ blob_append(pBlob, "", 1); zUtf8 = blob_str(pBlob) + bomSize; zUtf8 = fossil_unicode_to_utf8(zUtf8); blob_set_dynamic(pBlob, zUtf8); #if defined(_WIN32) }else if( useMbcs ){ zUtf8 = fossil_mbcs_to_utf8(blob_str(pBlob)); blob_reset(pBlob); blob_append(pBlob, zUtf8, -1); fossil_mbcs_free(zUtf8); #endif /* _WIN32 */ } } |
Changes to src/db.c.
︙ | ︙ | |||
313 314 315 316 317 318 319 320 321 322 323 324 325 326 | } int db_bind_double(Stmt *pStmt, const char *zParamName, double rValue){ return sqlite3_bind_double(pStmt->pStmt, paramIdx(pStmt, zParamName), rValue); } int db_bind_text(Stmt *pStmt, const char *zParamName, const char *zValue){ return sqlite3_bind_text(pStmt->pStmt, paramIdx(pStmt, zParamName), zValue, -1, SQLITE_STATIC); } int db_bind_null(Stmt *pStmt, const char *zParamName){ return sqlite3_bind_null(pStmt->pStmt, paramIdx(pStmt, zParamName)); } int db_bind_blob(Stmt *pStmt, const char *zParamName, Blob *pBlob){ return sqlite3_bind_blob(pStmt->pStmt, paramIdx(pStmt, zParamName), blob_buffer(pBlob), blob_size(pBlob), SQLITE_STATIC); | > > > > | 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 | } int db_bind_double(Stmt *pStmt, const char *zParamName, double rValue){ return sqlite3_bind_double(pStmt->pStmt, paramIdx(pStmt, zParamName), rValue); } int db_bind_text(Stmt *pStmt, const char *zParamName, const char *zValue){ return sqlite3_bind_text(pStmt->pStmt, paramIdx(pStmt, zParamName), zValue, -1, SQLITE_STATIC); } int db_bind_text16(Stmt *pStmt, const char *zParamName, const char *zValue){ return sqlite3_bind_text16(pStmt->pStmt, paramIdx(pStmt, zParamName), zValue, -1, SQLITE_STATIC); } int db_bind_null(Stmt *pStmt, const char *zParamName){ return sqlite3_bind_null(pStmt->pStmt, paramIdx(pStmt, zParamName)); } int db_bind_blob(Stmt *pStmt, const char *zParamName, Blob *pBlob){ return sqlite3_bind_blob(pStmt->pStmt, paramIdx(pStmt, zParamName), blob_buffer(pBlob), blob_size(pBlob), SQLITE_STATIC); |
︙ | ︙ |
Changes to src/diff.c.
︙ | ︙ | |||
1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 | if( diffFlags & DIFF_INVERT ){ Blob *pTemp = pA_Blob; pA_Blob = pB_Blob; pB_Blob = pTemp; } ignoreEolWs = (diffFlags & DIFF_IGNORE_EOLWS)!=0; /* Prepare the input files */ memset(&c, 0, sizeof(c)); c.aFrom = break_into_lines(blob_str(pA_Blob), blob_size(pA_Blob), &c.nFrom, ignoreEolWs); c.aTo = break_into_lines(blob_str(pB_Blob), blob_size(pB_Blob), &c.nTo, ignoreEolWs); | > > | 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 | if( diffFlags & DIFF_INVERT ){ Blob *pTemp = pA_Blob; pA_Blob = pB_Blob; pB_Blob = pTemp; } ignoreEolWs = (diffFlags & DIFF_IGNORE_EOLWS)!=0; blob_to_utf8_no_bom(pA_Blob, 0); blob_to_utf8_no_bom(pB_Blob, 0); /* Prepare the input files */ memset(&c, 0, sizeof(c)); c.aFrom = break_into_lines(blob_str(pA_Blob), blob_size(pA_Blob), &c.nFrom, ignoreEolWs); c.aTo = break_into_lines(blob_str(pB_Blob), blob_size(pB_Blob), &c.nTo, ignoreEolWs); |
︙ | ︙ |
Changes to src/info.c.
︙ | ︙ | |||
1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 | @ <iframe src="%R/raw/%T(blob_str(&downloadName))?name=%s(zUuid)" @ width="100%%" frameborder="0" marginwidth="0" marginheight="0" @ sandbox="allow-same-origin" @ onload="this.height = this.contentDocument.documentElement.scrollHeight;"> @ </iframe> }else{ style_submenu_element("Hex","Hex", "%s/hexdump?name=%s", g.zTop, zUuid); zMime = mimetype_from_content(&content); @ <blockquote> if( zMime==0 ){ const char *zLn = P("ln"); const char *z; | > < | 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 | @ <iframe src="%R/raw/%T(blob_str(&downloadName))?name=%s(zUuid)" @ width="100%%" frameborder="0" marginwidth="0" marginheight="0" @ sandbox="allow-same-origin" @ onload="this.height = this.contentDocument.documentElement.scrollHeight;"> @ </iframe> }else{ style_submenu_element("Hex","Hex", "%s/hexdump?name=%s", g.zTop, zUuid); blob_to_utf8_no_bom(&content, 0); zMime = mimetype_from_content(&content); @ <blockquote> if( zMime==0 ){ const char *zLn = P("ln"); const char *z; z = blob_str(&content); if( zLn ){ output_text_with_line_numbers(z, zLn); }else{ @ <pre> @ %h(z) @ </pre> |
︙ | ︙ |
Changes to src/utf8.c.
︙ | ︙ | |||
52 53 54 55 56 57 58 | ** Return a pointer to the translated text. ** Call fossil_unicode_free() to deallocate any memory used to store the ** returned pointer when done. */ char *fossil_unicode_to_utf8(const void *zUnicode){ #if defined(_WIN32) || defined(__CYGWIN__) int nByte = WideCharToMultiByte(CP_UTF8, 0, zUnicode, -1, 0, 0, 0, 0); | | < < < > > > > > | > > | < < < > < < < < | 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 93 94 95 96 97 98 99 100 101 102 103 | ** Return a pointer to the translated text. ** Call fossil_unicode_free() to deallocate any memory used to store the ** returned pointer when done. */ char *fossil_unicode_to_utf8(const void *zUnicode){ #if defined(_WIN32) || defined(__CYGWIN__) int nByte = WideCharToMultiByte(CP_UTF8, 0, zUnicode, -1, 0, 0, 0, 0); char *zUtf = fossil_malloc( nByte ); WideCharToMultiByte(CP_UTF8, 0, zUnicode, -1, zUtf, nByte, 0, 0); return zUtf; #else static Stmt q; char *zUtf8; db_static_prepare(&q, "SELECT :utf8"); db_bind_text16(&q, ":utf8", zUnicode); db_step(&q); zUtf8 = fossil_strdup(db_column_text(&q, 0)); db_reset(&q); return zUtf8; #endif } /* ** Translate UTF-8 to unicode for use in system calls. Return a pointer to the ** translated text.. Call fossil_unicode_free() to deallocate any memory ** used to store the returned pointer when done. */ void *fossil_utf8_to_unicode(const char *zUtf8){ #if defined(_WIN32) || defined(__CYGWIN__) int nByte = MultiByteToWideChar(CP_UTF8, 0, zUtf8, -1, 0, 0); wchar_t *zUnicode = fossil_malloc( nByte * 2 ); MultiByteToWideChar(CP_UTF8, 0, zUtf8, -1, zUnicode, nByte); return zUnicode; #else assert( 0 ); /* Never used in unix */ return fossil_strdup(zUtf8); /* TODO: implement for unix */ #endif } /* ** Deallocate any memory that was previously allocated by ** fossil_unicode_to_utf8(). */ void fossil_unicode_free(void *pOld){ fossil_free(pOld); } #if defined(__APPLE__) && !defined(WITHOUT_ICONV) # include <iconv.h> #endif /* |
︙ | ︙ |