feat(csv): add standard compliant CSV parser#77
Conversation
Replace naive parser logic with the new module. Includes RFC 4180 support for embedded newlines and proper quote escaping.
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly upgrades the CSV parsing functionality within the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a new, robust, RFC 4180-compliant CSV parser and integrates it into pretty-csv, replacing the previous naive implementation. The changes are a significant improvement, providing better error handling and support for complex CSV features like embedded newlines. The new csv module is well-designed with a state machine-based parser and includes comprehensive tests. The memory management is handled carefully. I have one suggestion to improve the clarity of the documentation for one of the parsing options.
docs/content/packages/csv.org
Outdated
| - =parseLine()= parses a single delimited line into fields | ||
| - =parseDocument()= parses a full input buffer into rows | ||
| - Configurable delimiter through =ParseOptions.delimiter= | ||
| - Optional empty-line skipping and CR trimming |
There was a problem hiding this comment.
The phrase "CR trimming" could be misleading. The trim_trailing_cr option doesn't trim carriage returns but rather controls whether a lone \r (not part of a \r\n sequence) is an error or part of the field's data. Clarifying this in the documentation would help users better understand the behavior, especially since it differs from typical line-based processing that might simply trim the character.
- Optional empty-line skipping and strict handling of lone carriage returns
There was a problem hiding this comment.
Pull request overview
Adds a new zigcli.csv package and wires pretty-csv to use it, replacing the previous ad-hoc line parser with an RFC 4180–aware state machine.
Changes:
- Export new
csvmodule fromzigcliand add a full-document CSV parser with quote/newline support. - Update
pretty-csvto parse viacsv.parseDocument()instead of splitting lines manually. - Add/refresh documentation and changelog entries; pass
-Dversionthrough release builds.
Reviewed changes
Copilot reviewed 9 out of 10 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| src/lib.zig | Exports the new zigcli.csv module. |
| src/csv.zig | Introduces CSV parsing API (parseLine, parseDocument) plus tests. |
| src/bin/pretty-csv.zig | Switches to the shared CSV parser and removes the old local parser. |
| docs/content/programs/pretty-csv.org | Updates pretty-csv feature documentation for RFC 4180 behavior. |
| docs/content/packages/csv.org | Adds package docs for the new csv module. |
| docs/content/packages/_index.org | Lists the new csv package in the packages index. |
| docs/content/install.org | Updates install docs to reflect the additional submodule. |
| docs/content/_index.org | Mentions the new csv package on the docs homepage. |
| CHANGELOG.md | Records the new csv package and behavior in the changelog. |
| .github/build-release.sh | Passes -Dversion to zig build for release artifacts. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| pub const ParseOptions = struct { | ||
| delimiter: u8 = ',', | ||
| skip_empty_lines: bool = false, | ||
| trim_trailing_cr: bool = true, | ||
| }; |
There was a problem hiding this comment.
ParseOptions.trim_trailing_cr is named like it will trim a trailing '\r', but the current parser never trims; it only treats a bare '\r' (not followed by '\n') as an InvalidRecordTerminator (and parseLine rejects any '\r' regardless). Either implement actual CR trimming where intended (e.g., allow/strip a final '\r' in parseLine inputs), or rename/remove this option so callers aren't misled.
src/csv.zig
Outdated
| test "parseDocument skips empty lines and trims trailing CR" { | ||
| const allocator = std.testing.allocator; | ||
| var document = try parseDocument(allocator, "a,b\r\n\r\n1,2\r\n", .{ | ||
| .skip_empty_lines = true, | ||
| }); | ||
| defer document.deinit(allocator); |
There was a problem hiding this comment.
The test name says it "trims trailing CR", but the input uses normal CRLF record terminators (no stray/trailing '\r' to trim). Consider renaming the test to match what it's asserting, or add a case that actually covers the intended CR-trimming behavior.
docs/content/packages/csv.org
Outdated
| The package also keeps a few explicit extensions for CLI use cases: | ||
|
|
||
| - Alternate delimiters such as TSV via =ParseOptions.delimiter= | ||
| - Optional empty-line skipping via =ParseOptions.skip_empty_lines= | ||
| - Acceptance of LF-only line endings in addition to RFC 4180 CRLF | ||
|
|
There was a problem hiding this comment.
This doc claims "CR trimming" as an extension, but the current implementation doesn't trim CR characters; it rejects a bare '\r' as error.InvalidRecordTerminator (and parseLine rejects '\r' entirely). Please update the documentation to reflect the actual behavior, or adjust the parser/API to provide the documented trimming behavior.
Add release-single.sh for isolated CI builds. Extend workflow to support matrix targets (Linux, macOS, Windows, FreeBSD). Remove trim_trailing_cr to enforce strict record terminators.
jiacai2050
force-pushed
the
feat-csv
branch
6 times, most recently
from
0f65d53 to
d3141f9
Compare
Replace naive parser logic with the new module. Includes RFC 4180 support for embedded newlines and proper quote escaping.