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

Handle quoted fields with embedded new lines. Sort separators by score

Browse Source 
rather than just standard deviation
This commit is contained in:
Tom Morris 2013-08-02 17:59:09 -04:00
parent f4ff227340
commit d7531bbbd8
1 changed files with 17 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
main/src/com/google/refine/importers/SeparatorBasedImporter.java
View File

@ -168,6 +168,7 @@ public class SeparatorBasedImporter extends TabularImportingParserBase {
return guessSeparator(file, encoding, false); // quotes off for backward compatibility return guessSeparator(file, encoding, false); // quotes off for backward compatibility
} }
// TODO: Move this to the CSV project?
static public Separator guessSeparator(File file, String encoding, boolean handleQuotes) { static public Separator guessSeparator(File file, String encoding, boolean handleQuotes) {
try { try {
InputStream is = new FileInputStream(file); InputStream is = new FileInputStream(file);
@ -190,7 +191,9 @@ public class SeparatorBasedImporter extends TabularImportingParserBase {
if (s.length() == 0) { if (s.length() == 0) {
continue; continue;
} }
lineCount++; if (!inQuote) {
lineCount++;
}
for (int i = 0; i < s.length(); i++) { for (int i = 0; i < s.length(); i++) {
char c = s.charAt(i); char c = s.charAt(i);
@ -212,10 +215,12 @@ public class SeparatorBasedImporter extends TabularImportingParserBase {
} }
} }
for (Separator separator : separators) { if (!inQuote) {
separator.totalCount += separator.currentLineCount; for (Separator separator : separators) {
separator.totalOfSquaredCount += separator.currentLineCount * separator.currentLineCount; separator.totalCount += separator.currentLineCount;
separator.currentLineCount = 0; separator.totalOfSquaredCount += separator.currentLineCount * separator.currentLineCount;
separator.currentLineCount = 0;
}
} }
} }
@ -231,14 +236,16 @@ public class SeparatorBasedImporter extends TabularImportingParserBase {
Collections.sort(separators, new Comparator<Separator>() { Collections.sort(separators, new Comparator<Separator>() {
@Override @Override
public int compare(Separator sep0, Separator sep1) { public int compare(Separator sep0, Separator sep1) {
return Double.compare(sep0.stddev, sep1.stddev); return Double.compare(sep0.stddev / sep0.averagePerLine,
sep1.stddev / sep1.averagePerLine);
} }
}); });
for (Separator separator : separators) {
if (separator.stddev / separator.averagePerLine < 0.1) { Separator separator = separators.get(0);
return separator; if (separator.stddev / separator.averagePerLine < 0.1) {
} return separator;
} }
} }
} finally { } finally {
lineNumberReader.close(); lineNumberReader.close();