Skip to content

Fix row count parsing for large 32-bit SAS files #96

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
abhi-2605 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix row count parsing for large 32-bit SAS files #96

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fff50cb
signed bit to unsigned to avoid overflow after 3B
abhi-2605 May 20, 2026
35c783c
Merge branch 'master' into parso-2.0.11-patched
abhi-2605 May 20, 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
40 changes: 30 additions & 10 deletions src/main/java/com/epam/parso/impl/SasFileParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,15 +194,15 @@ public final class SasFileParser {
/**
* The index of the current byte when reading the file.
*/
private int currentFilePosition;
private long currentFilePosition;
/**
* The index of the current column when reading the file.
*/
private int currentColumnNumber;
/**
* The index of the current row when reading the file.
*/
private int currentRowInFileIndex;
private long currentRowInFileIndex;
/**
* The index of the current row when reading the page.
*/
Expand Down Expand Up @@ -603,6 +603,7 @@ public Object[] readNext(List<String> columnNames) throws IOException {
if (currentRowInFileIndex++ >= sasFileProperties.getRowCount() || eof) {
return null;
}
currentRowInFileIndex++;
int bitOffset = sasFileProperties.isU64() ? PAGE_BIT_OFFSET_X64 : PAGE_BIT_OFFSET_X86;
currentRow = null;
switch (currentPageType) {
Expand Down Expand Up @@ -944,7 +945,7 @@ private List<byte[]> getBytesFromFile(Long[] offset, Integer[] length) throws IO
} catch (EOFException e) {
eof = true;
}
currentFilePosition = (int) (long) offset[i] + length[i];
currentFilePosition = offset[i] + length[i];
vars.add(temp);
}
} else {
Expand All @@ -967,13 +968,24 @@ private List<byte[]> getBytesFromFile(Long[] offset, Integer[] length) throws IO
* for convenience.
*/
private long correctLongProcess(ByteBuffer byteBuffer) {
if (sasFileProperties.isU64()) {
return byteBuffer.getLong();
} else {
return byteBuffer.getInt();
if (sasFileProperties.isU64()) {
return byteBuffer.getLong();
} else {
return byteBuffer.getInt(); // signed
}
}
/**
* Reads a 32-bit unsigned integer from the provided {@link ByteBuffer} and returns it as a {@code long}.
* <p>
* SAS stores some counters (e.g., rowCount) as 32-bit values that should be interpreted as unsigned.
*
* @param byteBuffer buffer positioned at the start of the 4-byte unsigned int
* @return unsigned 32-bit value widened to long (0..4294967295)
*/

private long readUnsignedInt(ByteBuffer byteBuffer) {
return ((long) byteBuffer.getInt()) & 0xFFFFFFFFL;
}
/**
* The function to convert an array of bytes with any order of bytes into {@link ByteBuffer}.
* {@link ByteBuffer} has the order of bytes defined in the file located at the
Expand Down Expand Up @@ -1456,13 +1468,21 @@ public void processSubheader(long subheaderOffset, long subheaderLength) throws
if (sasFileProperties.getRowLength() == 0) {
sasFileProperties.setRowLength(bytesToLong(vars.get(0)));
}
// if (sasFileProperties.getRowCount() == 0) {
// sasFileProperties.setRowCount(bytesToLong(vars.get(1)));
// }
if (sasFileProperties.getRowCount() == 0) {
sasFileProperties.setRowCount(bytesToLong(vars.get(1)));
ByteBuffer bb = byteArrayToByteBuffer(vars.get(1));
long rc = sasFileProperties.isU64() ? bb.getLong() : readUnsignedInt(bb);
sasFileProperties.setRowCount(rc);
}
if (sasFileProperties.getMixPageRowCount() == 0) {
sasFileProperties.setMixPageRowCount(bytesToLong(vars.get(2)));
ByteBuffer bb = byteArrayToByteBuffer(vars.get(2));
long mrc = sasFileProperties.isU64()
? bb.getLong()
: readUnsignedInt(bb);
sasFileProperties.setMixPageRowCount(mrc);
}

fileLabelOffset = bytesToShort(vars.get(3));
fileLabelLength = bytesToShort(vars.get(4));

Expand Down