Skip to content

feat: add support for column-based reading of XLS files #981

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sapienza88 wants to merge 6 commits into
base: main
Choose a base branch
from
Open

feat: add support for column-based reading of XLS files #981

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b394c30
feature: number and sstlabel with column support
Jul 30, 2026
b32f394
remove null checks for sheet holder and sheet
Aug 5, 2026
44d0058
feat: adding filtering capability for columns for additional typeset:…
Aug 5, 2026
636961f
fix CI: missing import
Aug 5, 2026
2060a5d
fix CI : add missing imports
Aug 6, 2026
fb3df39
address reviewing comments : revert NOTE
Aug 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion ...-sheet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/BlankRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@

package org.apache.fesod.sheet.analysis.v03.handlers;

import java.util.List;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
import org.apache.fesod.sheet.context.xls.XlsReadContext;
import org.apache.fesod.sheet.metadata.data.ReadCellData;
Expand All @@ -39,9 +40,21 @@ public class BlankRecordHandler extends AbstractXlsRecordHandler implements Igno
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
BlankRecord br = (BlankRecord) record;
int originalColumnIndex = br.getColumn();

List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}
xlsReadContext
.xlsReadSheetHolder()
.getCellMap()
.put((int) br.getColumn(), ReadCellData.newEmptyInstance(br.getRow(), (int) br.getColumn()));
.put(targetColumnIndex, ReadCellData.newEmptyInstance(br.getRow(), targetColumnIndex));
}
}
16 changes: 14 additions & 2 deletions ...heet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/BoolErrRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@

package org.apache.fesod.sheet.analysis.v03.handlers;

import java.util.List;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
import org.apache.fesod.sheet.context.xls.XlsReadContext;
import org.apache.fesod.sheet.enums.RowTypeEnum;
Expand All @@ -40,11 +41,22 @@ public class BoolErrRecordHandler extends AbstractXlsRecordHandler implements Ig
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
BoolErrRecord ber = (BoolErrRecord) record;
int originalColumnIndex = ber.getColumn();
List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}
xlsReadContext
.xlsReadSheetHolder()
.getCellMap()
.put((int) ber.getColumn(), ReadCellData.newInstance(ber.getBooleanValue(), ber.getRow(), (int)
ber.getColumn()));
.put(targetColumnIndex, ReadCellData.newInstance(ber.getBooleanValue(), ber.getRow(), (int)
targetColumnIndex));
xlsReadContext.xlsReadSheetHolder().setTempRowType(RowTypeEnum.DATA);
}
}
14 changes: 13 additions & 1 deletion ...-sheet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/DummyRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
package org.apache.fesod.sheet.analysis.v03.handlers;

import java.util.LinkedHashMap;
import java.util.List;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
import org.apache.fesod.sheet.context.xls.XlsReadContext;
import org.apache.fesod.sheet.enums.RowTypeEnum;
Expand Down Expand Up @@ -58,11 +59,22 @@ public void processRecord(XlsReadContext xlsReadContext, Record record) {
xlsReadSheetHolder.setTempRowType(RowTypeEnum.EMPTY);
} else if (record instanceof MissingCellDummyRecord) {
MissingCellDummyRecord mcdr = (MissingCellDummyRecord) record;
int originalColumnIndex = mcdr.getColumn();
List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}
// Some abnormal XLS, in the case of data already exist, or there will be a "MissingCellDummyRecord"
// records, so if the existing data, empty data is ignored
xlsReadSheetHolder
.getCellMap()
.putIfAbsent(mcdr.getColumn(), ReadCellData.newEmptyInstance(mcdr.getRow(), mcdr.getColumn()));
.putIfAbsent(targetColumnIndex, ReadCellData.newEmptyInstance(mcdr.getRow(), targetColumnIndex));
}
}
}
24 changes: 19 additions & 5 deletions ...heet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/FormulaRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
package org.apache.fesod.sheet.analysis.v03.handlers;

import java.math.BigDecimal;
import java.util.List;
import java.util.Map;
import lombok.extern.slf4j.Slf4j;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
Expand Down Expand Up @@ -53,10 +54,23 @@ public class FormulaRecordHandler extends AbstractXlsRecordHandler implements Ig
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
FormulaRecord frec = (FormulaRecord) record;
int originalColumnIndex = frec.getColumn();

List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}

Map<Integer, Cell> cellMap = xlsReadContext.xlsReadSheetHolder().getCellMap();
ReadCellData<?> tempCellData = new ReadCellData<>();
tempCellData.setRowIndex(frec.getRow());
tempCellData.setColumnIndex((int) frec.getColumn());
tempCellData.setColumnIndex(targetColumnIndex);
CellType cellType = CellType.forInt(frec.getCachedResultType());
String formulaValue = null;
try {
Expand Down Expand Up @@ -98,21 +112,21 @@ public void processRecord(XlsReadContext xlsReadContext, Record record) {
.getGlobalConfiguration()
.getLocale()));
tempCellData.setDataFormatData(dataFormatData);
cellMap.put((int) frec.getColumn(), tempCellData);
cellMap.put(targetColumnIndex, tempCellData);
break;
case ERROR:
tempCellData.setType(CellDataTypeEnum.ERROR);
tempCellData.setStringValue(ERROR);
cellMap.put((int) frec.getColumn(), tempCellData);
cellMap.put(targetColumnIndex, tempCellData);
break;
case BOOLEAN:
tempCellData.setType(CellDataTypeEnum.BOOLEAN);
tempCellData.setBooleanValue(frec.getCachedBooleanValue());
cellMap.put((int) frec.getColumn(), tempCellData);
cellMap.put(targetColumnIndex, tempCellData);
break;
default:
tempCellData.setType(CellDataTypeEnum.EMPTY);
cellMap.put((int) frec.getColumn(), tempCellData);
cellMap.put(targetColumnIndex, tempCellData);
break;
}
}
Expand Down
16 changes: 15 additions & 1 deletion ...-sheet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/LabelRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@

package org.apache.fesod.sheet.analysis.v03.handlers;

import java.util.List;
import org.apache.fesod.common.util.StringUtils;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
import org.apache.fesod.sheet.context.xls.XlsReadContext;
Expand All @@ -41,6 +42,19 @@ public class LabelRecordHandler extends AbstractXlsRecordHandler implements Igno
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
LabelRecord lrec = (LabelRecord) record;
int originalColumnIndex = lrec.getColumn();

List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}

String data = lrec.getValue();
if (data != null) {
GlobalConfiguration globalConfiguration =
Expand All @@ -54,7 +68,7 @@ public void processRecord(XlsReadContext xlsReadContext, Record record) {
xlsReadContext
.xlsReadSheetHolder()
.getCellMap()
.put((int) lrec.getColumn(), ReadCellData.newInstance(data, lrec.getRow(), (int) lrec.getColumn()));
.put(targetColumnIndex, ReadCellData.newInstance(data, lrec.getRow(), targetColumnIndex));
xlsReadContext.xlsReadSheetHolder().setTempRowType(RowTypeEnum.DATA);
}
}
22 changes: 17 additions & 5 deletions ...eet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/LabelSstRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@

package org.apache.fesod.sheet.analysis.v03.handlers;

import java.util.List;
import java.util.Map;
import org.apache.fesod.common.util.StringUtils;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
Expand All @@ -45,17 +46,28 @@ public class LabelSstRecordHandler extends AbstractXlsRecordHandler implements I
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
LabelSSTRecord lsrec = (LabelSSTRecord) record;
int originalColumnIndex = lsrec.getColumn();

List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}

ReadCache readCache = xlsReadContext.readWorkbookHolder().getReadCache();
Map<Integer, Cell> cellMap = xlsReadContext.xlsReadSheetHolder().getCellMap();
if (readCache == null) {
cellMap.put(
(int) lsrec.getColumn(), ReadCellData.newEmptyInstance(lsrec.getRow(), (int) lsrec.getColumn()));
cellMap.put(targetColumnIndex, ReadCellData.newEmptyInstance(lsrec.getRow(), targetColumnIndex));
return;
}
String data = readCache.get(lsrec.getSSTIndex());
if (data == null) {
cellMap.put(
(int) lsrec.getColumn(), ReadCellData.newEmptyInstance(lsrec.getRow(), (int) lsrec.getColumn()));
cellMap.put(targetColumnIndex, ReadCellData.newEmptyInstance(lsrec.getRow(), targetColumnIndex));
return;
}

Expand All @@ -66,7 +78,7 @@ public void processRecord(XlsReadContext xlsReadContext, Record record) {
} else if (globalConfiguration.getAutoTrim()) {
data = data.trim();
}
cellMap.put((int) lsrec.getColumn(), ReadCellData.newInstance(data, lsrec.getRow(), (int) lsrec.getColumn()));
cellMap.put(targetColumnIndex, ReadCellData.newInstance(data, lsrec.getRow(), targetColumnIndex));
xlsReadContext.xlsReadSheetHolder().setTempRowType(RowTypeEnum.DATA);
}
}
18 changes: 16 additions & 2 deletions ...sheet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/NumberRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
package org.apache.fesod.sheet.analysis.v03.handlers;

import java.math.BigDecimal;
import java.util.List;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
import org.apache.fesod.sheet.constant.BuiltinFormats;
import org.apache.fesod.sheet.context.xls.XlsReadContext;
Expand All @@ -43,8 +44,21 @@ public class NumberRecordHandler extends AbstractXlsRecordHandler implements Ign
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
NumberRecord nr = (NumberRecord) record;
int originalColumnIndex = nr.getColumn();

List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}

ReadCellData<?> cellData =
ReadCellData.newInstanceOriginal(BigDecimal.valueOf(nr.getValue()), nr.getRow(), (int) nr.getColumn());
ReadCellData.newInstanceOriginal(BigDecimal.valueOf(nr.getValue()), nr.getRow(), targetColumnIndex);
short dataFormat = (short) xlsReadContext
.xlsReadWorkbookHolder()
.getFormatTrackingHSSFListener()
Expand All @@ -59,7 +73,7 @@ public void processRecord(XlsReadContext xlsReadContext, Record record) {
.getFormatString(nr),
xlsReadContext.readSheetHolder().getGlobalConfiguration().getLocale()));
cellData.setDataFormatData(dataFormatData);
xlsReadContext.xlsReadSheetHolder().getCellMap().put((int) nr.getColumn(), cellData);
xlsReadContext.xlsReadSheetHolder().getCellMap().put(targetColumnIndex, cellData);
xlsReadContext.xlsReadSheetHolder().setTempRowType(RowTypeEnum.DATA);
}
}
15 changes: 14 additions & 1 deletion fesod-sheet/src/main/java/org/apache/fesod/sheet/analysis/v03/handlers/RkRecordHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@

package org.apache.fesod.sheet.analysis.v03.handlers;

import java.util.List;
import org.apache.fesod.sheet.analysis.v03.IgnorableXlsRecordHandler;
import org.apache.fesod.sheet.context.xls.XlsReadContext;
import org.apache.fesod.sheet.metadata.data.ReadCellData;
Expand All @@ -39,9 +40,21 @@ public class RkRecordHandler extends AbstractXlsRecordHandler implements Ignorab
@Override
public void processRecord(XlsReadContext xlsReadContext, Record record) {
RKRecord re = (RKRecord) record;
int originalColumnIndex = re.getColumn();

List<Integer> includeColumnIndexes =
xlsReadContext.readSheetHolder().getReadSheet().getColumnIndexes();

int targetColumnIndex = originalColumnIndex;
if (includeColumnIndexes != null) {
targetColumnIndex = includeColumnIndexes.indexOf(originalColumnIndex);
if (targetColumnIndex < 0) {
return;
}
}
xlsReadContext
.xlsReadSheetHolder()
.getCellMap()
.put((int) re.getColumn(), ReadCellData.newEmptyInstance(re.getRow(), (int) re.getColumn()));
.put(targetColumnIndex, ReadCellData.newEmptyInstance(re.getRow(), targetColumnIndex));
}
}
Loading
Loading