1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 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 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
|
/******************************************************************************
* $Id: cpl_csv.cpp 25340 2012-12-21 20:30:21Z rouault $
*
* Project: CPL - Common Portability Library
* Purpose: CSV (comma separated value) file access.
* Author: Frank Warmerdam, warmerdam@pobox.com
*
******************************************************************************
* Copyright (c) 1999, Frank Warmerdam
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included
* in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
****************************************************************************/
#include "cpl_csv.h"
#include "cpl_conv.h"
#include "cpl_multiproc.h"
#include "gdal_csv.h"
CPL_CVSID("$Id: cpl_csv.cpp 25340 2012-12-21 20:30:21Z rouault $");
/* ==================================================================== */
/* The CSVTable is a persistant set of info about an open CSV */
/* table. While it doesn't currently maintain a record index, */
/* or in-memory copy of the table, it could be changed to do so */
/* in the future. */
/* ==================================================================== */
typedef struct ctb {
FILE *fp;
struct ctb *psNext;
char *pszFilename;
char **papszFieldNames;
char **papszRecFields;
int iLastLine;
int bNonUniqueKey;
/* Cache for whole file */
int nLineCount;
char **papszLines;
int *panLineIndex;
char *pszRawData;
} CSVTable;
static void CSVDeaccessInternal( CSVTable **ppsCSVTableList, int bCanUseTLS, const char * pszFilename );
/************************************************************************/
/* CSVFreeTLS() */
/************************************************************************/
static void CSVFreeTLS(void* pData)
{
CSVDeaccessInternal( (CSVTable **)pData, FALSE, NULL );
CPLFree(pData);
}
/* It would likely be better to share this list between threads, but
that will require some rework. */
/************************************************************************/
/* CSVAccess() */
/* */
/* This function will fetch a handle to the requested table. */
/* If not found in the ``open table list'' the table will be */
/* opened and added to the list. Eventually this function may */
/* become public with an abstracted return type so that */
/* applications can set options about the table. For now this */
/* isn't done. */
/************************************************************************/
static CSVTable *CSVAccess( const char * pszFilename )
{
CSVTable *psTable;
FILE *fp;
/* -------------------------------------------------------------------- */
/* Fetch the table, and allocate the thread-local pointer to it */
/* if there isn't already one. */
/* -------------------------------------------------------------------- */
CSVTable **ppsCSVTableList;
ppsCSVTableList = (CSVTable **) CPLGetTLS( CTLS_CSVTABLEPTR );
if( ppsCSVTableList == NULL )
{
ppsCSVTableList = (CSVTable **) CPLCalloc(1,sizeof(CSVTable*));
CPLSetTLSWithFreeFunc( CTLS_CSVTABLEPTR, ppsCSVTableList, CSVFreeTLS );
}
/* -------------------------------------------------------------------- */
/* Is the table already in the list. */
/* -------------------------------------------------------------------- */
for( psTable = *ppsCSVTableList;
psTable != NULL;
psTable = psTable->psNext )
{
if( EQUAL(psTable->pszFilename,pszFilename) )
{
/*
* Eventually we should consider promoting to the front of
* the list to accelerate frequently accessed tables.
*/
return( psTable );
}
}
/* -------------------------------------------------------------------- */
/* If not, try to open it. */
/* -------------------------------------------------------------------- */
fp = VSIFOpen( pszFilename, "rb" );
if( fp == NULL )
return NULL;
/* -------------------------------------------------------------------- */
/* Create an information structure about this table, and add to */
/* the front of the list. */
/* -------------------------------------------------------------------- */
psTable = (CSVTable *) CPLCalloc(sizeof(CSVTable),1);
psTable->fp = fp;
psTable->pszFilename = CPLStrdup( pszFilename );
psTable->bNonUniqueKey = FALSE; /* as far as we know now */
psTable->psNext = *ppsCSVTableList;
*ppsCSVTableList = psTable;
/* -------------------------------------------------------------------- */
/* Read the table header record containing the field names. */
/* -------------------------------------------------------------------- */
psTable->papszFieldNames = CSVReadParseLine( fp );
return( psTable );
}
/************************************************************************/
/* CSVDeaccess() */
/************************************************************************/
static void CSVDeaccessInternal( CSVTable **ppsCSVTableList, int bCanUseTLS, const char * pszFilename )
{
CSVTable *psLast, *psTable;
if( ppsCSVTableList == NULL )
return;
/* -------------------------------------------------------------------- */
/* A NULL means deaccess all tables. */
/* -------------------------------------------------------------------- */
if( pszFilename == NULL )
{
while( *ppsCSVTableList != NULL )
CSVDeaccessInternal( ppsCSVTableList, bCanUseTLS, (*ppsCSVTableList)->pszFilename );
return;
}
/* -------------------------------------------------------------------- */
/* Find this table. */
/* -------------------------------------------------------------------- */
psLast = NULL;
for( psTable = *ppsCSVTableList;
psTable != NULL && !EQUAL(psTable->pszFilename,pszFilename);
psTable = psTable->psNext )
{
psLast = psTable;
}
if( psTable == NULL )
{
if (bCanUseTLS)
CPLDebug( "CPL_CSV", "CPLDeaccess( %s ) - no match.", pszFilename );
return;
}
/* -------------------------------------------------------------------- */
/* Remove the link from the list. */
/* -------------------------------------------------------------------- */
if( psLast != NULL )
psLast->psNext = psTable->psNext;
else
*ppsCSVTableList = psTable->psNext;
/* -------------------------------------------------------------------- */
/* Free the table. */
/* -------------------------------------------------------------------- */
if( psTable->fp != NULL )
VSIFClose( psTable->fp );
CSLDestroy( psTable->papszFieldNames );
CSLDestroy( psTable->papszRecFields );
CPLFree( psTable->pszFilename );
CPLFree( psTable->panLineIndex );
CPLFree( psTable->pszRawData );
CPLFree( psTable->papszLines );
CPLFree( psTable );
if (bCanUseTLS)
CPLReadLine( NULL );
}
void CSVDeaccess( const char * pszFilename )
{
CSVTable **ppsCSVTableList;
/* -------------------------------------------------------------------- */
/* Fetch the table, and allocate the thread-local pointer to it */
/* if there isn't already one. */
/* -------------------------------------------------------------------- */
ppsCSVTableList = (CSVTable **) CPLGetTLS( CTLS_CSVTABLEPTR );
CSVDeaccessInternal(ppsCSVTableList, TRUE, pszFilename);
}
/************************************************************************/
/* CSVSplitLine() */
/* */
/* Tokenize a CSV line into fields in the form of a string */
/* list. This is used instead of the CPLTokenizeString() */
/* because it provides correct CSV escaping and quoting */
/* semantics. */
/************************************************************************/
static char **CSVSplitLine( const char *pszString, char chDelimiter )
{
char **papszRetList = NULL;
char *pszToken;
int nTokenMax, nTokenLen;
pszToken = (char *) CPLCalloc(10,1);
nTokenMax = 10;
while( pszString != NULL && *pszString != '\0' )
{
int bInString = FALSE;
nTokenLen = 0;
/* Try to find the next delimeter, marking end of token */
for( ; *pszString != '\0'; pszString++ )
{
/* End if this is a delimeter skip it and break. */
if( !bInString && *pszString == chDelimiter )
{
pszString++;
break;
}
if( *pszString == '"' )
{
if( !bInString || pszString[1] != '"' )
{
bInString = !bInString;
continue;
}
else /* doubled quotes in string resolve to one quote */
{
pszString++;
}
}
if( nTokenLen >= nTokenMax-2 )
{
nTokenMax = nTokenMax * 2 + 10;
pszToken = (char *) CPLRealloc( pszToken, nTokenMax );
}
pszToken[nTokenLen] = *pszString;
nTokenLen++;
}
pszToken[nTokenLen] = '\0';
papszRetList = CSLAddString( papszRetList, pszToken );
/* If the last token is an empty token, then we have to catch
* it now, otherwise we won't reenter the loop and it will be lost.
*/
if ( *pszString == '\0' && *(pszString-1) == chDelimiter )
{
papszRetList = CSLAddString( papszRetList, "" );
}
}
if( papszRetList == NULL )
papszRetList = (char **) CPLCalloc(sizeof(char *),1);
CPLFree( pszToken );
return papszRetList;
}
/************************************************************************/
/* CSVFindNextLine() */
/* */
/* Find the start of the next line, while at the same time zero */
/* terminating this line. Take into account that there may be */
/* newline indicators within quoted strings, and that quotes */
/* can be escaped with a backslash. */
/************************************************************************/
static char *CSVFindNextLine( char *pszThisLine )
{
int nQuoteCount = 0, i;
for( i = 0; pszThisLine[i] != '\0'; i++ )
{
if( pszThisLine[i] == '\"'
&& (i == 0 || pszThisLine[i-1] != '\\') )
nQuoteCount++;
if( (pszThisLine[i] == 10 || pszThisLine[i] == 13)
&& (nQuoteCount % 2) == 0 )
break;
}
while( pszThisLine[i] == 10 || pszThisLine[i] == 13 )
pszThisLine[i++] = '\0';
if( pszThisLine[i] == '\0' )
return NULL;
else
return pszThisLine + i;
}
/************************************************************************/
/* CSVIngest() */
/* */
/* Load entire file into memory and setup index if possible. */
/************************************************************************/
static void CSVIngest( const char *pszFilename )
{
CSVTable *psTable = CSVAccess( pszFilename );
int nFileLen, i, nMaxLineCount, iLine = 0;
char *pszThisLine;
if( psTable->pszRawData != NULL )
return;
/* -------------------------------------------------------------------- */
/* Ingest whole file. */
/* -------------------------------------------------------------------- */
VSIFSeek( psTable->fp, 0, SEEK_END );
nFileLen = VSIFTell( psTable->fp );
VSIRewind( psTable->fp );
psTable->pszRawData = (char *) CPLMalloc(nFileLen+1);
if( (int) VSIFRead( psTable->pszRawData, 1, nFileLen, psTable->fp )
!= nFileLen )
{
CPLFree( psTable->pszRawData );
psTable->pszRawData = NULL;
CPLError( CE_Failure, CPLE_FileIO, "Read of file %s failed.",
psTable->pszFilename );
return;
}
psTable->pszRawData[nFileLen] = '\0';
/* -------------------------------------------------------------------- */
/* Get count of newlines so we can allocate line array. */
/* -------------------------------------------------------------------- */
nMaxLineCount = 0;
for( i = 0; i < nFileLen; i++ )
{
if( psTable->pszRawData[i] == 10 )
nMaxLineCount++;
}
psTable->papszLines = (char **) CPLCalloc(sizeof(char*),nMaxLineCount);
/* -------------------------------------------------------------------- */
/* Build a list of record pointers into the raw data buffer */
/* based on line terminators. Zero terminate the line */
/* strings. */
/* -------------------------------------------------------------------- */
/* skip header line */
pszThisLine = CSVFindNextLine( psTable->pszRawData );
while( pszThisLine != NULL && iLine < nMaxLineCount )
{
psTable->papszLines[iLine++] = pszThisLine;
pszThisLine = CSVFindNextLine( pszThisLine );
}
psTable->nLineCount = iLine;
/* -------------------------------------------------------------------- */
/* Allocate and populate index array. Ensure they are in */
/* ascending order so that binary searches can be done on the */
/* array. */
/* -------------------------------------------------------------------- */
psTable->panLineIndex = (int *) CPLMalloc(sizeof(int)*psTable->nLineCount);
for( i = 0; i < psTable->nLineCount; i++ )
{
psTable->panLineIndex[i] = atoi(psTable->papszLines[i]);
if( i > 0 && psTable->panLineIndex[i] < psTable->panLineIndex[i-1] )
{
CPLFree( psTable->panLineIndex );
psTable->panLineIndex = NULL;
break;
}
}
psTable->iLastLine = -1;
/* -------------------------------------------------------------------- */
/* We should never need the file handle against, so close it. */
/* -------------------------------------------------------------------- */
VSIFClose( psTable->fp );
psTable->fp = NULL;
}
/************************************************************************/
/* CSVDetectSeperator() */
/************************************************************************/
/** Detect which field separator is used.
*
* Currently, it can detect comma, semicolon or tabulation. In case of
* ambiguity or no separator found, comma will be considered as the separator.
*
* @return ',', ';' or '\t'
*/
char CSVDetectSeperator (const char* pszLine)
{
int bInString = FALSE;
char chDelimiter = '\0';
for( ; *pszLine != '\0'; pszLine++ )
{
if( !bInString && (*pszLine == ',' || *pszLine == ';' || *pszLine == '\t'))
{
if (chDelimiter == '\0')
chDelimiter = *pszLine;
else if (chDelimiter != *pszLine)
{
/* The separator is not consistent on the line. */
CPLDebug("CSV", "Inconsistent separator. '%c' and '%c' found. Using ',' as default",
chDelimiter, *pszLine);
chDelimiter = ',';
break;
}
}
else if( *pszLine == '"' )
{
if( !bInString || pszLine[1] != '"' )
{
bInString = !bInString;
continue;
}
else /* doubled quotes in string resolve to one quote */
{
pszLine++;
}
}
}
if (chDelimiter == '\0')
chDelimiter = ',';
return chDelimiter;
}
/************************************************************************/
/* CSVReadParseLine() */
/* */
/* Read one line, and return split into fields. The return */
/* result is a stringlist, in the sense of the CSL functions. */
/************************************************************************/
char **CSVReadParseLine( FILE * fp )
{
return CSVReadParseLine2(fp, ',');
}
char **CSVReadParseLine2( FILE * fp, char chDelimiter )
{
const char *pszLine;
char *pszWorkLine;
char **papszReturn;
CPLAssert( fp != NULL );
if( fp == NULL )
return( NULL );
pszLine = CPLReadLine( fp );
if( pszLine == NULL )
return( NULL );
/* -------------------------------------------------------------------- */
/* If there are no quotes, then this is the simple case. */
/* Parse, and return tokens. */
/* -------------------------------------------------------------------- */
if( strchr(pszLine,'\"') == NULL )
return CSVSplitLine( pszLine, chDelimiter );
/* -------------------------------------------------------------------- */
/* We must now count the quotes in our working string, and as */
/* long as it is odd, keep adding new lines. */
/* -------------------------------------------------------------------- */
pszWorkLine = CPLStrdup( pszLine );
int i = 0, nCount = 0;
int nWorkLineLength = strlen(pszWorkLine);
while( TRUE )
{
for( ; pszWorkLine[i] != '\0'; i++ )
{
if( pszWorkLine[i] == '\"'
&& (i == 0 || pszWorkLine[i-1] != '\\') )
nCount++;
}
if( nCount % 2 == 0 )
break;
pszLine = CPLReadLine( fp );
if( pszLine == NULL )
break;
int nLineLen = strlen(pszLine);
char* pszWorkLineTmp = (char *)
VSIRealloc(pszWorkLine,
nWorkLineLength + nLineLen + 2);
if (pszWorkLineTmp == NULL)
break;
pszWorkLine = pszWorkLineTmp;
strcat( pszWorkLine + nWorkLineLength, "\n" ); // This gets lost in CPLReadLine().
strcat( pszWorkLine + nWorkLineLength, pszLine );
nWorkLineLength += nLineLen + 1;
}
papszReturn = CSVSplitLine( pszWorkLine, chDelimiter );
CPLFree( pszWorkLine );
return papszReturn;
}
/************************************************************************/
/* CSVCompare() */
/* */
/* Compare a field to a search value using a particular */
/* criteria. */
/************************************************************************/
static int CSVCompare( const char * pszFieldValue, const char * pszTarget,
CSVCompareCriteria eCriteria )
{
if( eCriteria == CC_ExactString )
{
return( strcmp( pszFieldValue, pszTarget ) == 0 );
}
else if( eCriteria == CC_ApproxString )
{
return( EQUAL( pszFieldValue, pszTarget ) );
}
else if( eCriteria == CC_Integer )
{
return( atoi(pszFieldValue) == atoi(pszTarget) );
}
return FALSE;
}
/************************************************************************/
/* CSVScanLines() */
/* */
/* Read the file scanline for lines where the key field equals */
/* the indicated value with the suggested comparison criteria. */
/* Return the first matching line split into fields. */
/************************************************************************/
char **CSVScanLines( FILE *fp, int iKeyField, const char * pszValue,
CSVCompareCriteria eCriteria )
{
char **papszFields = NULL;
int bSelected = FALSE, nTestValue;
CPLAssert( pszValue != NULL );
CPLAssert( iKeyField >= 0 );
CPLAssert( fp != NULL );
nTestValue = atoi(pszValue);
while( !bSelected ) {
papszFields = CSVReadParseLine( fp );
if( papszFields == NULL )
return( NULL );
if( CSLCount( papszFields ) < iKeyField+1 )
{
/* not selected */
}
else if( eCriteria == CC_Integer
&& atoi(papszFields[iKeyField]) == nTestValue )
{
bSelected = TRUE;
}
else
{
bSelected = CSVCompare( papszFields[iKeyField], pszValue,
eCriteria );
}
if( !bSelected )
{
CSLDestroy( papszFields );
papszFields = NULL;
}
}
return( papszFields );
}
/************************************************************************/
/* CSVScanLinesIndexed() */
/* */
/* Read the file scanline for lines where the key field equals */
/* the indicated value with the suggested comparison criteria. */
/* Return the first matching line split into fields. */
/************************************************************************/
static char **
CSVScanLinesIndexed( CSVTable *psTable, int nKeyValue )
{
int iTop, iBottom, iMiddle, iResult = -1;
CPLAssert( psTable->panLineIndex != NULL );
/* -------------------------------------------------------------------- */
/* Find target record with binary search. */
/* -------------------------------------------------------------------- */
iTop = psTable->nLineCount-1;
iBottom = 0;
while( iTop >= iBottom )
{
iMiddle = (iTop + iBottom) / 2;
if( psTable->panLineIndex[iMiddle] > nKeyValue )
iTop = iMiddle - 1;
else if( psTable->panLineIndex[iMiddle] < nKeyValue )
iBottom = iMiddle + 1;
else
{
iResult = iMiddle;
// if a key is not unique, select the first instance of it.
while( iResult > 0
&& psTable->panLineIndex[iResult-1] == nKeyValue )
{
psTable->bNonUniqueKey = TRUE;
iResult--;
}
break;
}
}
if( iResult == -1 )
return NULL;
/* -------------------------------------------------------------------- */
/* Parse target line, and update iLastLine indicator. */
/* -------------------------------------------------------------------- */
psTable->iLastLine = iResult;
return CSVSplitLine( psTable->papszLines[iResult], ',' );
}
/************************************************************************/
/* CSVScanLinesIngested() */
/* */
/* Read the file scanline for lines where the key field equals */
/* the indicated value with the suggested comparison criteria. */
/* Return the first matching line split into fields. */
/************************************************************************/
static char **
CSVScanLinesIngested( CSVTable *psTable, int iKeyField, const char * pszValue,
CSVCompareCriteria eCriteria )
{
char **papszFields = NULL;
int bSelected = FALSE, nTestValue;
CPLAssert( pszValue != NULL );
CPLAssert( iKeyField >= 0 );
nTestValue = atoi(pszValue);
/* -------------------------------------------------------------------- */
/* Short cut for indexed files. */
/* -------------------------------------------------------------------- */
if( iKeyField == 0 && eCriteria == CC_Integer
&& psTable->panLineIndex != NULL )
return CSVScanLinesIndexed( psTable, nTestValue );
/* -------------------------------------------------------------------- */
/* Scan from in-core lines. */
/* -------------------------------------------------------------------- */
while( !bSelected && psTable->iLastLine+1 < psTable->nLineCount ) {
psTable->iLastLine++;
papszFields = CSVSplitLine( psTable->papszLines[psTable->iLastLine], ',' );
if( CSLCount( papszFields ) < iKeyField+1 )
{
/* not selected */
}
else if( eCriteria == CC_Integer
&& atoi(papszFields[iKeyField]) == nTestValue )
{
bSelected = TRUE;
}
else
{
bSelected = CSVCompare( papszFields[iKeyField], pszValue,
eCriteria );
}
if( !bSelected )
{
CSLDestroy( papszFields );
papszFields = NULL;
}
}
return( papszFields );
}
/************************************************************************/
/* CSVGetNextLine() */
/* */
/* Fetch the next line of a CSV file based on a passed in */
/* filename. Returns NULL at end of file, or if file is not */
/* really established. */
/************************************************************************/
char **CSVGetNextLine( const char *pszFilename )
{
CSVTable *psTable;
/* -------------------------------------------------------------------- */
/* Get access to the table. */
/* -------------------------------------------------------------------- */
CPLAssert( pszFilename != NULL );
psTable = CSVAccess( pszFilename );
if( psTable == NULL )
return NULL;
/* -------------------------------------------------------------------- */
/* If we use CSVGetNextLine() we can pretty much assume we have */
/* a non-unique key. */
/* -------------------------------------------------------------------- */
psTable->bNonUniqueKey = TRUE;
/* -------------------------------------------------------------------- */
/* Do we have a next line available? This only works for */
/* ingested tables I believe. */
/* -------------------------------------------------------------------- */
if( psTable->iLastLine+1 >= psTable->nLineCount )
return NULL;
psTable->iLastLine++;
CSLDestroy( psTable->papszRecFields );
psTable->papszRecFields =
CSVSplitLine( psTable->papszLines[psTable->iLastLine], ',' );
return psTable->papszRecFields;
}
/************************************************************************/
/* CSVScanFile() */
/* */
/* Scan a whole file using criteria similar to above, but also */
/* taking care of file opening and closing. */
/************************************************************************/
char **CSVScanFile( const char * pszFilename, int iKeyField,
const char * pszValue, CSVCompareCriteria eCriteria )
{
CSVTable *psTable;
/* -------------------------------------------------------------------- */
/* Get access to the table. */
/* -------------------------------------------------------------------- */
CPLAssert( pszFilename != NULL );
if( iKeyField < 0 )
return NULL;
psTable = CSVAccess( pszFilename );
if( psTable == NULL )
return NULL;
CSVIngest( pszFilename );
/* -------------------------------------------------------------------- */
/* Does the current record match the criteria? If so, just */
/* return it again. */
/* -------------------------------------------------------------------- */
if( iKeyField >= 0
&& iKeyField < CSLCount(psTable->papszRecFields)
&& CSVCompare(pszValue,psTable->papszRecFields[iKeyField],eCriteria)
&& !psTable->bNonUniqueKey )
{
return psTable->papszRecFields;
}
/* -------------------------------------------------------------------- */
/* Scan the file from the beginning, replacing the ``current */
/* record'' in our structure with the one that is found. */
/* -------------------------------------------------------------------- */
psTable->iLastLine = -1;
CSLDestroy( psTable->papszRecFields );
if( psTable->pszRawData != NULL )
psTable->papszRecFields =
CSVScanLinesIngested( psTable, iKeyField, pszValue, eCriteria );
else
{
VSIRewind( psTable->fp );
CPLReadLine( psTable->fp ); /* throw away the header line */
psTable->papszRecFields =
CSVScanLines( psTable->fp, iKeyField, pszValue, eCriteria );
}
return( psTable->papszRecFields );
}
/************************************************************************/
/* CPLGetFieldId() */
/* */
/* Read the first record of a CSV file (rewinding to be sure), */
/* and find the field with the indicated name. Returns -1 if */
/* it fails to find the field name. Comparison is case */
/* insensitive, but otherwise exact. After this function has */
/* been called the file pointer will be positioned just after */
/* the first record. */
/************************************************************************/
int CSVGetFieldId( FILE * fp, const char * pszFieldName )
{
char **papszFields;
int i;
CPLAssert( fp != NULL && pszFieldName != NULL );
VSIRewind( fp );
papszFields = CSVReadParseLine( fp );
for( i = 0; papszFields != NULL && papszFields[i] != NULL; i++ )
{
if( EQUAL(papszFields[i],pszFieldName) )
{
CSLDestroy( papszFields );
return i;
}
}
CSLDestroy( papszFields );
return -1;
}
/************************************************************************/
/* CSVGetFileFieldId() */
/* */
/* Same as CPLGetFieldId(), except that we get the file based */
/* on filename, rather than having an existing handle. */
/************************************************************************/
int CSVGetFileFieldId( const char * pszFilename, const char * pszFieldName )
{
CSVTable *psTable;
int i;
/* -------------------------------------------------------------------- */
/* Get access to the table. */
/* -------------------------------------------------------------------- */
CPLAssert( pszFilename != NULL );
psTable = CSVAccess( pszFilename );
if( psTable == NULL )
return -1;
/* -------------------------------------------------------------------- */
/* Find the requested field. */
/* -------------------------------------------------------------------- */
for( i = 0;
psTable->papszFieldNames != NULL
&& psTable->papszFieldNames[i] != NULL;
i++ )
{
if( EQUAL(psTable->papszFieldNames[i],pszFieldName) )
{
return i;
}
}
return -1;
}
/************************************************************************/
/* CSVScanFileByName() */
/* */
/* Same as CSVScanFile(), but using a field name instead of a */
/* field number. */
/************************************************************************/
char **CSVScanFileByName( const char * pszFilename,
const char * pszKeyFieldName,
const char * pszValue, CSVCompareCriteria eCriteria )
{
int iKeyField;
iKeyField = CSVGetFileFieldId( pszFilename, pszKeyFieldName );
if( iKeyField == -1 )
return NULL;
return( CSVScanFile( pszFilename, iKeyField, pszValue, eCriteria ) );
}
/************************************************************************/
/* CSVGetField() */
/* */
/* The all-in-one function to fetch a particular field value */
/* from a CSV file. Note this function will return an empty */
/* string, rather than NULL if it fails to find the desired */
/* value for some reason. The caller can't establish that the */
/* fetch failed. */
/************************************************************************/
const char *CSVGetField( const char * pszFilename,
const char * pszKeyFieldName,
const char * pszKeyFieldValue,
CSVCompareCriteria eCriteria,
const char * pszTargetField )
{
CSVTable *psTable;
char **papszRecord;
int iTargetField;
/* -------------------------------------------------------------------- */
/* Find the table. */
/* -------------------------------------------------------------------- */
psTable = CSVAccess( pszFilename );
if( psTable == NULL )
return "";
/* -------------------------------------------------------------------- */
/* Find the correct record. */
/* -------------------------------------------------------------------- */
papszRecord = CSVScanFileByName( pszFilename, pszKeyFieldName,
pszKeyFieldValue, eCriteria );
if( papszRecord == NULL )
return "";
/* -------------------------------------------------------------------- */
/* Figure out which field we want out of this. */
/* -------------------------------------------------------------------- */
iTargetField = CSVGetFileFieldId( pszFilename, pszTargetField );
if( iTargetField < 0 )
return "";
if( iTargetField >= CSLCount( papszRecord ) )
return "";
return( papszRecord[iTargetField] );
}
/************************************************************************/
/* GDALDefaultCSVFilename() */
/************************************************************************/
typedef struct
{
char szPath[512];
int bCSVFinderInitialized;
} DefaultCSVFileNameTLS;
const char * GDALDefaultCSVFilename( const char *pszBasename )
{
/* -------------------------------------------------------------------- */
/* Do we already have this file accessed? If so, just return */
/* the existing path without any further probing. */
/* -------------------------------------------------------------------- */
CSVTable **ppsCSVTableList;
ppsCSVTableList = (CSVTable **) CPLGetTLS( CTLS_CSVTABLEPTR );
if( ppsCSVTableList != NULL )
{
CSVTable *psTable;
int nBasenameLen = strlen(pszBasename);
for( psTable = *ppsCSVTableList;
psTable != NULL;
psTable = psTable->psNext )
{
int nFullLen = strlen(psTable->pszFilename);
if( nFullLen > nBasenameLen
&& strcmp(psTable->pszFilename+nFullLen-nBasenameLen,
pszBasename) == 0
&& strchr("/\\",psTable->pszFilename[+nFullLen-nBasenameLen-1])
!= NULL )
{
return psTable->pszFilename;
}
}
}
/* -------------------------------------------------------------------- */
/* Otherwise we need to look harder for it. */
/* -------------------------------------------------------------------- */
DefaultCSVFileNameTLS* pTLSData =
(DefaultCSVFileNameTLS *) CPLGetTLS( CTLS_CSVDEFAULTFILENAME );
if (pTLSData == NULL)
{
pTLSData = (DefaultCSVFileNameTLS*) CPLCalloc(1, sizeof(DefaultCSVFileNameTLS));
CPLSetTLS( CTLS_CSVDEFAULTFILENAME, pTLSData, TRUE );
}
FILE *fp = NULL;
const char *pszResult;
pszResult = CPLFindFile( "epsg_csv", pszBasename );
if( pszResult != NULL )
return pszResult;
if( !pTLSData->bCSVFinderInitialized )
{
pTLSData->bCSVFinderInitialized = TRUE;
if( CPLGetConfigOption("GEOTIFF_CSV",NULL) != NULL )
CPLPushFinderLocation( CPLGetConfigOption("GEOTIFF_CSV",NULL));
if( CPLGetConfigOption("GDAL_DATA",NULL) != NULL )
CPLPushFinderLocation( CPLGetConfigOption("GDAL_DATA",NULL) );
pszResult = CPLFindFile( "epsg_csv", pszBasename );
if( pszResult != NULL )
return pszResult;
}
if( (fp = fopen( "csv/horiz_cs.csv", "rt" )) != NULL )
{
strcpy( pTLSData->szPath, "csv/" );
CPLStrlcat( pTLSData->szPath, pszBasename, sizeof(pTLSData->szPath) );
}
else
{
#ifdef GDAL_PREFIX
#ifdef MACOSX_FRAMEWORK
strcpy( pTLSData->szPath, GDAL_PREFIX "/Resources/epsg_csv/" );
CPLStrlcat( pTLSData->szPath, pszBasename, sizeof(pTLSData->szPath) );
#else
strcpy( pTLSData->szPath, GDAL_PREFIX "/share/epsg_csv/" );
CPLStrlcat( pTLSData->szPath, pszBasename, sizeof(pTLSData->szPath) );
#endif
#else
strcpy( pTLSData->szPath, "/usr/local/share/epsg_csv/" );
CPLStrlcat( pTLSData->szPath, pszBasename, sizeof(pTLSData->szPath) );
#endif
if( (fp = fopen( pTLSData->szPath, "rt" )) == NULL )
CPLStrlcpy( pTLSData->szPath, pszBasename, sizeof(pTLSData->szPath) );
}
if( fp != NULL )
fclose( fp );
return( pTLSData->szPath );
}
/************************************************************************/
/* CSVFilename() */
/* */
/* Return the full path to a particular CSV file. This will */
/* eventually be something the application can override. */
/************************************************************************/
CPL_C_START
static const char *(*pfnCSVFilenameHook)(const char *) = NULL;
CPL_C_END
const char * CSVFilename( const char *pszBasename )
{
if( pfnCSVFilenameHook == NULL )
return GDALDefaultCSVFilename( pszBasename );
else
return( pfnCSVFilenameHook( pszBasename ) );
}
/************************************************************************/
/* SetCSVFilenameHook() */
/* */
/* Applications can use this to set a function that will */
/* massage CSV filenames. */
/************************************************************************/
/**
* Override CSV file search method.
*
* @param pfnNewHook The pointer to a function which will return the
* full path for a given filename.
*
This function allows an application to override how the GTIFGetDefn() and related function find the CSV (Comma Separated
Value) values required. The pfnHook argument should be a pointer to a function that will take in a CSV filename and return a
full path to the file. The returned string should be to an internal static buffer so that the caller doesn't have to free the result.
<b>Example:</b><br>
The listgeo utility uses the following override function if the user
specified a CSV file directory with the -t commandline switch (argument
put into CSVDirName). <p>
<pre>
...
SetCSVFilenameHook( CSVFileOverride );
...
static const char *CSVFileOverride( const char * pszInput )
{
static char szPath[1024];
#ifdef WIN32
sprintf( szPath, "%s\\%s", CSVDirName, pszInput );
#else
sprintf( szPath, "%s/%s", CSVDirName, pszInput );
#endif
return( szPath );
}
</pre>
*/
CPL_C_START
void SetCSVFilenameHook( const char *(*pfnNewHook)( const char * ) )
{
pfnCSVFilenameHook = pfnNewHook;
}
CPL_C_END
|