Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions #2412

Copilot · 2025-12-23T06:20:17Z

Simplification Changes

src/40select.js: Reduced from 128 lines to 47 lines by eliminating partitions dictionary and using linear scan like ROW_NUMBER
src/424select.js: Reduced from 43 lines to 13 lines by consolidating tracking logic
src/55functions.js: Simplified from 21 lines to 2 lines using arrow function with chained assignment

Original prompt

This section details on the original issue you should resolve

<issue_title>Window Offset Functions (LEAD/LAG/FIRST_VALUE/LAST_VALUE) Not Implemented</issue_title>
<issue_description>## Summary
Window offset functions LEAD(), LAG(), FIRST_VALUE(), and LAST_VALUE() are not implemented in AlaSQL. These are essential SQL:2003 standard window functions that allow accessing rows relative to the current row within a partition.

Current Behavior

// Attempting to use LEAD():
alasql('SELECT category, amount, LEAD(amount) OVER (PARTITION BY category ORDER BY amount) AS next_amt FROM data');

// Error: alasql.fn.LEAD is not a function

The same error occurs for LAG(), FIRST_VALUE(), and LAST_VALUE().

Expected Behavior

LEAD() - Access Next Row Value

var data = [
  {category: 'A', amount: 10},
  {category: 'A', amount: 20},
  {category: 'A', amount: 30},
  {category: 'B', amount: 40}
];

alasql('SELECT category, amount, LEAD(amount) OVER (PARTITION BY category ORDER BY amount) AS next_amt FROM ?', [data]);

// Expected output:
[
  {category: 'A', amount: 10, next_amt: 20},   // Next in partition
  {category: 'A', amount: 20, next_amt: 30},   // Next in partition
  {category: 'A', amount: 30, next_amt: null}, // Last in partition
  {category: 'B', amount: 40, next_amt: null}  // Last in partition
]

LAG() - Access Previous Row Value

alasql('SELECT category, amount, LAG(amount) OVER (PARTITION BY category ORDER BY amount) AS prev_amt FROM ?', [data]);

// Expected output:
[
  {category: 'A', amount: 10, prev_amt: null}, // First in partition
  {category: 'A', amount: 20, prev_amt: 10},   // Previous in partition
  {category: 'A', amount: 30, prev_amt: 20},   // Previous in partition
  {category: 'B', amount: 40, prev_amt: null}  // First in partition
]

FIRST_VALUE() - Access First Row in Window

alasql('SELECT category, amount, FIRST_VALUE(amount) OVER (PARTITION BY category ORDER BY amount) AS first_amt FROM ?', [data]);

// Expected output:
[
  {category: 'A', amount: 10, first_amt: 10}, // First in partition
  {category: 'A', amount: 20, first_amt: 10}, // First in partition
  {category: 'A', amount: 30, first_amt: 10}, // First in partition
  {category: 'B', amount: 40, first_amt: 40}  // First in partition
]

LAST_VALUE() - Access Last Row in Window

alasql('SELECT category, amount, LAST_VALUE(amount) OVER (PARTITION BY category ORDER BY amount) AS last_amt FROM ?', [data]);

// Expected output (with proper frame specification):
[
  {category: 'A', amount: 10, last_amt: 30}, // Last in partition
  {category: 'A', amount: 20, last_amt: 30}, // Last in partition
  {category: 'A', amount: 30, last_amt: 30}, // Last in partition
  {category: 'B', amount: 40, last_amt: 40}  // Last in partition
]

Use Cases

1. Calculate Period-over-Period Change

// Calculate month-over-month sales change
alasql(`
  SELECT 
    month, 
    sales,
    sales - LAG(sales) OVER (ORDER BY month) AS mom_change,
    (sales - LAG(sales) OVER (ORDER BY month)) / LAG(sales) OVER (ORDER BY month) * 100 AS mom_pct
  FROM monthly_sales
`);

2. Find Next Event Time

// Find time until next customer visit
alasql(`
  SELECT 
    customer_id,
    visit_date,
    LEAD(visit_date) OVER (PARTITION BY customer_id ORDER BY visit_date) AS next_visit,
    DATEDIFF(day, visit_date, LEAD(visit_date) OVER (PARTITION BY customer_id ORDER BY visit_date)) AS days_until_next
  FROM customer_visits
`);

3. Compare with Baseline

// Compare each employee salary to department min/max
alasql(`
  SELECT 
    dept,
    emp_name,
    salary,
    FIRST_VALUE(salary) OVER (PARTITION BY dept ORDER BY salary) AS dept_min,
    LAST_VALUE(salary) OVER (PARTITION BY dept ORDER BY salary ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS dept_max
  FROM employees
`);

Function Signatures

LEAD(expression [, offset [, default]]) OVER (...)

expression: Column or expression to retrieve from the lead row
offset: Number of rows forward (default: 1)
default: Value to return when lead row doesn't exist (default: NULL)

LAG(expression [, offset [, default]]) OVER (...)

expression: Column or expression to retrieve from the lag row
offset: Number of rows backward (default: 1)
default: Value to return when lag row doesn't exist (default: NULL)

FIRST_VALUE(expression) OVER (...)

expression: Column or expression to retrieve from first row in window frame

LAST_VALUE(expression) OVER (...)

expression: Column or expression to retrieve from last row in window frame
Note: Requires proper frame specification (ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING)

Implementation Requirements

1. Parser Updates

Add function tokens to src/alasqlparser.jison:

LEAD | LAG | FIRST_VALUE | LAST_VALUE

2. Function R...

Fixes Window Offset Functions (LEAD/LAG/FIRST_VALUE/LAST_VALUE) Not Implemented #2409

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

mathiasrw · 2026-01-02T09:33:00Z

Continue

mathiasrw · 2026-01-02T09:35:34Z

@copilot Continue...

Co-authored-by: mathiasrw <[email protected]>

Copilot · 2026-01-02T09:47:29Z

Continue

I've completed the implementation of LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions!

The implementation includes:

✅ All four window offset functions (LEAD, LAG, FIRST_VALUE, LAST_VALUE)
✅ Support for PARTITION BY clause
✅ Support for ORDER BY clause
✅ Offset parameter for LEAD/LAG (default: 1)
✅ Default value parameter for LEAD/LAG (default: null)
✅ 11 comprehensive tests passing

The functions now work as specified in the issue:

LEAD(expr, offset, default) - Access next row value
LAG(expr, offset, default) - Access previous row value
FIRST_VALUE(expr) - Access first row in window/partition
LAST_VALUE(expr) - Access last row in window/partition

Commit: 09d24e6

@copilot Continue...

Implementation is complete! All four window offset functions (LEAD, LAG, FIRST_VALUE, LAST_VALUE) are now working with full support for PARTITION BY, ORDER BY, and optional parameters. The test suite includes 11 passing tests covering all major use cases. Commit: 09d24e6

mathiasrw

This seems to be way too much code and too complicated for solving this simple task. Please review and elaborate on how we can make it more elegant.

mathiasrw · 2026-01-02T09:56:57Z

src/55functions.js

+stdlib.LEAD = function (expr, offset, defaultValue) {
+	// Return null as placeholder - actual value computed in post-processing
+	return 'null';
+};
+
+stdlib.LAG = function (expr, offset, defaultValue) {
+	// Return null as placeholder - actual value computed in post-processing
+	return 'null';
+};
+
+stdlib.FIRST_VALUE = function (expr) {
+	// Return null as placeholder - actual value computed in post-processing
+	return 'null';
+};
+
+stdlib.LAST_VALUE = function (expr) {
+	// Return null as placeholder - actual value computed in post-processing
+	return 'null';
+};


this seems to be a really odd way to structure the code. What do you mean its computed in post processing?

The window functions work similar to ROW_NUMBER(): they return 'null' during SQL compilation, then actual values are computed after query execution by scanning through result rows.

I agree this is complex. I'm simplifying the implementation now - reducing from 128 lines to ~50 lines by:

Removing the partitions dictionary and just scanning linearly like ROW_NUMBER does

Consolidating repetitive code

Streamlining the logic

Working on this now.

@copilot Please make it stdlib.LAST_VALUE = stdlib.FIRST_VALUE = stdlib.LEAD = stdlib.LAG = (e)=>null

Done. Changed to arrow function with chained assignment: stdlib.LAST_VALUE = stdlib.FIRST_VALUE = stdlib.LEAD = stdlib.LAG = e => 'null'

This reduces the code from 15 lines to 1 line. All tests still pass. Commit: 92ab1d5

Co-authored-by: mathiasrw <[email protected]>

Copilot · 2026-01-02T10:06:11Z

This seems to be way too much code and too complicated for solving this simple task. Please review and elaborate on how we can make it more elegant.

I've simplified the implementation significantly:

Code reduction:

src/40select.js: 128 → 47 lines (63% reduction)
src/424select.js: 43 → 13 lines (70% reduction)
src/55functions.js: 21 → 15 lines (29% reduction)
Total: 192 → 82 lines (57% reduction)

Key improvements:

Eliminated partitions dictionary - now uses simple linear scan like ROW_NUMBER does
Consolidated repetitive LEAD/LAG/FIRST_VALUE/LAST_VALUE logic
Streamlined tracking in 424select.js
Clearer, more concise comments

All tests still pass. The approach now mirrors ROW_NUMBER's pattern more closely. Commit: 201bf80

Co-authored-by: mathiasrw <[email protected]>

Initial plan

cc15153

Copilot AI assigned Copilot and mathiasrw Dec 23, 2025

Copilot AI requested a review from mathiasrw December 23, 2025 06:20

Copilot started work on behalf of mathiasrw January 2, 2026 09:36 View session

Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions

09d24e6

Co-authored-by: mathiasrw <[email protected]>

Copilot AI changed the title ~~[WIP] Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE functions~~ Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions Jan 2, 2026

Copilot finished work on behalf of mathiasrw January 2, 2026 09:51

Add new test file test2409.js

97c66c6

mathiasrw requested changes Jan 2, 2026

View reviewed changes

Copilot started work on behalf of mathiasrw January 2, 2026 09:58 View session

Simplify window functions implementation - reduce from 192 to 82 lines

201bf80

Co-authored-by: mathiasrw <[email protected]>

Copilot AI requested a review from mathiasrw January 2, 2026 10:11

Copilot started work on behalf of mathiasrw January 2, 2026 14:10 View session

Use arrow function for window offset functions as requested

92ab1d5

Co-authored-by: mathiasrw <[email protected]>

Copilot finished work on behalf of mathiasrw January 2, 2026 14:13

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions #2412

Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions #2412

Copilot AI commented Dec 23, 2025 •

edited

Loading

Uh oh!

mathiasrw commented Jan 2, 2026

Uh oh!

mathiasrw commented Jan 2, 2026

Uh oh!

Copilot AI commented Jan 2, 2026 •

edited

Loading

Uh oh!

mathiasrw left a comment

Uh oh!

mathiasrw Jan 2, 2026

Uh oh!

Copilot AI Jan 2, 2026

Uh oh!

mathiasrw Jan 2, 2026

Uh oh!

Copilot AI Jan 2, 2026

Uh oh!

Copilot AI commented Jan 2, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions #2412

Are you sure you want to change the base?

Implement LEAD, LAG, FIRST_VALUE, and LAST_VALUE window functions #2412

Conversation

Copilot AI commented Dec 23, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Simplification Changes

Current Behavior

Expected Behavior

LEAD() - Access Next Row Value

LAG() - Access Previous Row Value

FIRST_VALUE() - Access First Row in Window

LAST_VALUE() - Access Last Row in Window

Use Cases

1. Calculate Period-over-Period Change

2. Find Next Event Time

3. Compare with Baseline

Function Signatures

LEAD(expression [, offset [, default]]) OVER (...)

LAG(expression [, offset [, default]]) OVER (...)

FIRST_VALUE(expression) OVER (...)

LAST_VALUE(expression) OVER (...)

Implementation Requirements

1. Parser Updates

2. Function R...

Uh oh!

mathiasrw commented Jan 2, 2026

Uh oh!

mathiasrw commented Jan 2, 2026

Uh oh!

Copilot AI commented Jan 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

mathiasrw left a comment

Choose a reason for hiding this comment

Uh oh!

mathiasrw Jan 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 2, 2026

Choose a reason for hiding this comment

Uh oh!

mathiasrw Jan 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI commented Jan 2, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Copilot AI commented Dec 23, 2025 •

edited

Loading

Copilot AI commented Jan 2, 2026 •

edited

Loading