Add StructuredTable by DISTREAT · Pull Request #12 · DISTREAT/zig-csv

DISTREAT · 2026-01-18T01:51:07Z

No description provided.

This allows for inserting data on an empty Table.

Copilot

Pull request overview

This PR adds a new StructuredTable type that enables type-safe parsing and manipulation of CSV data through compile-time schema validation. The existing Table implementation has been refactored into separate modules to support the new functionality while maintaining backward compatibility through re-exports.

Changes:

Introduced StructuredTable generic type that maps CSV data to user-defined struct types with automatic type conversion and validation
Refactored monolithic src/root.zig into separate table.zig and schema.zig modules for better organization
Added comprehensive test suite for the new StructuredTable functionality and updated README documentation with usage examples

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
src/root.zig	Converted to thin re-export module that exposes both Table and StructuredTable APIs
src/table.zig	Extracted core Table implementation with bug fix for getColumnCount signature
src/schema.zig	New module implementing StructuredTable with type-safe CSV parsing and serialization
src/tests/root.zig	New test harness that imports individual test files
src/tests/table.zig	Updated table tests with corrected import and updated API usage
src/tests/schema.zig	Comprehensive test suite for StructuredTable covering parsing, editing, and error handling
build.zig	Updated test configuration to use new test structure with module import
README.md	Added extensive documentation and examples for both StructuredTable and Table APIs

Comments suppressed due to low confidence (1)

src/tests/table.zig:5

The StructuredTable constant is imported but never used in this test file. Since this file only contains tests for the Table type (not StructuredTable), this import should be removed.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

src/tests/schema.zig

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 6 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

src/schema.zig

Copilot · 2026-01-18T02:12:46Z

src/schema.zig

+        pub fn getRow(self: Self, row_index: usize) TableError!ParseResult(table_schema) {
+            if (row_index >= self.getRowCount()) return TableError.RowNotFound;
+            var out: table_schema = undefined;
+            inline for (schema_info.@"struct".fields) |field| {
+                const field_name = field.name;
+                const column_indexes = self.table.findColumnIndexesByValue(self.allocator, 0, field_name) catch return ParseResult(table_schema){
+                    .@"error" = .{
+                        .kind = StructureError.MissingColumn,
+                        .field_name = field_name,
+                        .field_type = @typeName(field.type),
+                        .csv_value = null,
+                    },
+                };
+                defer self.allocator.free(column_indexes);
+                if (column_indexes.len > 1) return ParseResult(table_schema){
+                    .@"error" = .{
+                        .kind = StructureError.AmbiguousColumn,
+                        .field_name = field_name,
+                        .field_type = @typeName(field.type),
+                        .csv_value = null,
+                    },
+                };
+                const rows = self.table.getColumnByIndex(self.allocator, column_indexes[0]) catch return ParseResult(table_schema){
+                    .@"error" = .{
+                        .kind = StructureError.MissingColumn,
+                        .field_name = field_name,
+                        .field_type = @typeName(field.type),
+                        .csv_value = null,
+                    },
+                };
+                defer self.allocator.free(rows);
+                const value = rows[row_index + 1];
+                const parsed = (&self).deserializeCsvValue(field.type, value) catch |err| return ParseResult(table_schema){
+                    .@"error" = .{
+                        .kind = err,
+                        .field_name = field_name,
+                        .field_type = @typeName(field.type),
+                        .csv_value = value,
+                    },
+                };
+                @field(out, field_name) = parsed;
+            }
+            return ParseResult(table_schema){
+                .ok = .{
+                    .value = out,
+                },
+            };
+        }


Performance concern: the function searches for each field's column index by value on every invocation, using findColumnIndexesByValue which performs a linear search. For tables with many fields or when this function is called frequently in a loop, this results in O(n*m) complexity where n is the number of fields and m is the number of columns. Consider caching the column index mapping after the first lookup to improve performance.

Performance is not in scope atm.

Copilot · 2026-01-18T02:12:47Z

src/schema.zig

+        pub fn editRow(self: *Self, row_index: usize, row: table_schema) TableError!ParseResult(table_schema) {
+            if (row_index >= self.getRowCount()) return TableError.RowNotFound;
+            inline for (schema_info.@"struct".fields) |field| {
+                const field_name = field.name;
+                const column_indexes = self.table.findColumnIndexesByValue(self.allocator, 0, field_name) catch return ParseResult(table_schema){
+                    .@"error" = .{
+                        .kind = StructureError.MissingColumn,
+                        .field_name = field_name,
+                        .field_type = @typeName(field.type),
+                        .csv_value = null,
+                    },
+                };
+                defer self.allocator.free(column_indexes);
+                if (column_indexes.len > 1) return ParseResult(table_schema){
+                    .@"error" = .{
+                        .kind = StructureError.AmbiguousColumn,
+                        .field_name = field_name,
+                        .field_type = @typeName(field.type),
+                        .csv_value = null,
+                    },
+                };
+                const column_index = column_indexes[0];
+                const table_index = headerAwareToTableIndex(row_index);
+                const value = try self.serializeCsvValue(field.type, @field(row, field_name));
+                try self.table.replaceValue(table_index, column_index, value);
+            }
+            return ParseResult(table_schema){
+                .ok = .{
+                    .value = row,
+                },
+            };
+        }


Performance concern: the function searches for each field's column index by value on every invocation, using findColumnIndexesByValue which performs a linear search. For tables with many fields or when this function is called frequently in a loop, this results in O(n*m) complexity where n is the number of fields and m is the number of columns. Consider caching the column index mapping after the first lookup to improve performance.

Performance is not in scope at the moment.

src/schema.zig

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 8 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-01-18T02:31:35Z

src/schema.zig

+                .bool => {
+                    const lower = std.ascii.allocLowerString(self.allocator, value) catch return TableError.OutOfMemory;
+                    defer self.allocator.free(lower);
+                    for ([_][]const u8{ "true", "1", "yes", "y" }) |true_word| {
+                        if (std.mem.eql(u8, true_word, lower)) {
+                            return true;
+                        }
+                    }
+                    for ([_][]const u8{ "false", "0", "no", "n" }) |false_word| {
+                        if (std.mem.eql(u8, false_word, lower)) {
+                            return false;
+                        }
+                    }
+                    return StructureError.UnexpectedType;
+                },


Memory allocated by std.ascii.allocLowerString is correctly freed with defer. However, this is called every time a boolean value is parsed. For better performance, consider converting the value to lowercase in-place in a small stack buffer since bool values are typically short strings.

Not in scope

README.md

src/schema.zig

src/tests/schema.zig

DISTREAT added 7 commits January 17, 2026 18:16

fix: remove NoData error type

1294edd

This allows for inserting data on an empty Table.

feat: add StructuredTable

3ca5404

fix: invalid row count check for findColumnIndexesByValue

1ac5832

fix: use mem.indexOf instead of mem.count

0a9eb17

refactor: add helpers for converting to and from row index

debfd26

feat: avoid circular import

94683b3

test: split tests into table and schema

7d820f6

DISTREAT self-assigned this Jan 18, 2026

DISTREAT added the enhancement New feature or request label Jan 18, 2026

DISTREAT linked an issue Jan 18, 2026 that may be closed by this pull request

Support Serialization and Deserialization of CSV Rows via Structs #9

Closed

DISTREAT force-pushed the comptime branch 2 times, most recently from c159527 to e132315 Compare January 18, 2026 02:00

feat(StructuredTable): add support for option type

bb41da8

DISTREAT force-pushed the comptime branch from e132315 to bb41da8 Compare January 18, 2026 02:01

DISTREAT requested a review from Copilot January 18, 2026 02:02

Copilot started reviewing on behalf of DISTREAT January 18, 2026 02:02 View session

Copilot AI reviewed Jan 18, 2026

View reviewed changes

src/tests/schema.zig Outdated Show resolved Hide resolved

src/tests/schema.zig Outdated Show resolved Hide resolved

test: remove duplicate test

2576e6d

DISTREAT requested a review from Copilot January 18, 2026 02:09

Copilot started reviewing on behalf of DISTREAT January 18, 2026 02:09 View session

Copilot AI reviewed Jan 18, 2026

View reviewed changes

DISTREAT added 2 commits January 18, 2026 03:26

docs: fix invalid zig syntax

75b922a

fix(StructuredTable): conversion of all errors to OutOfMemory

c85ed3c

DISTREAT requested a review from Copilot January 18, 2026 02:27

Copilot started reviewing on behalf of DISTREAT January 18, 2026 02:27 View session

Copilot AI reviewed Jan 18, 2026

View reviewed changes

fix(StructuredTable): compile error invalid type name

01a2439

DISTREAT merged commit 2291a4f into master Jan 18, 2026
2 checks passed

DISTREAT deleted the comptime branch January 18, 2026 02:37

Conversation

DISTREAT commented Jan 18, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI Jan 18, 2026

Choose a reason for hiding this comment

Uh oh!

DISTREAT Jan 18, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 18, 2026

Choose a reason for hiding this comment

Uh oh!

DISTREAT Jan 18, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Jan 18, 2026

Choose a reason for hiding this comment

Uh oh!

DISTREAT Jan 18, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant