s434730/RandomSec
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fixed csv importer to handle escaped quotation marks ("").

Browse Source 
git-svn-id: http://google-refine.googlecode.com/svn/trunk@257 7d457c2a-affb-35e4-300a-418c747d4874
This commit is contained in:
David Huynh 2010-03-09 19:10:55 +00:00
parent 8ce21461cb
commit 2bac6844e2
1 changed files with 25 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
src/main/java/com/metaweb/gridworks/importers/ImporterUtilities.java
View File

@ -35,14 +35,31 @@ public class ImporterUtilities {
String text = null;
if (line.charAt(start) == '"') {
int next = line.indexOf('"', start + 1);
if (next < 0) {
text = line.substring(start);
start = line.length();
} else {
text = line.substring(start, next + 1);
start = next + 2;
}
StringBuffer sb = new StringBuffer();
start++; // skip over "
while (start < line.length()) {
int quote = line.indexOf('"', start);
if (quote < 0) {
sb.append(line.substring(start));
start = line.length();
break;
} else {
if (quote < line.length() - 1 && line.charAt(quote + 1) == '"') {
sb.append(line.substring(start, quote + 1)); // include " as well
start = quote + 2;
} else {
sb.append(line.substring(start, quote));
start = quote + 1;
if (start < line.length() && line.charAt(start) == ',') {
start++; // skip ,
}
break;
}
}
}
text = sb.toString();
} else {
int next = line.indexOf(',', start);
if (next < 0) {