feat: add CsvDecoder to support streaming CSV parsing

[devin-ai-integration]

Add CsvDecoder to support streaming CSV parsing with configurable delimiter and encoding.

Link to Devin run: https://app.devin.ai/sessions/452c02a6b9e449ab863d5ad2747cc7b1
Requested by: [email protected]

[devin-ai-integration]

🤖 Devin AI Engineer

Original prompt from [email protected]:

Hey @Devin, can you please add a new Decoder to the Airbyte Python CDK (<https://github.com/airbytehq/airbyte-python-cdk>)?

More details on how and where you should add it:
• Start by defining the model in YAML component schema and regenerating the python classes:
    ◦ Add CsvDecoder everywhere where XmlDecoder is also supported
• CsvDecoder should support parameters for delimeter (default to ","), encoding (default to utf-8).
• Add code to model_to_component_factory to instanciate the CsvDecoder

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add "(aside)" to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[natikgadzhi]

This looks good, but you also need to add CsvDecoder as an option to all the spots in the schema that accept XmlDecoder as an option.

[natikgadzhi]

@coderabbitai review please?

[natikgadzhi]

@aaronsteers I'm not sure why CI checks don't seem to be in progress — anything I am missing? Do they want some form of human approval?

[coderabbitai]

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Get the PR diff to understand the changes
gh pr diff 321

# Look for any new CSV-related files
fd -e py csv

# Search for test files related to CSV
fd test.*csv

# Check if there are any documentation changes
fd -e md

Length of output: 81135

---

🏁 Script executed:

#!/bin/bash
# Get the CsvDecoder implementation
cat airbyte_cdk/sources/declarative/decoders/csv_decoder.py

# Check for tests
fd -t f "test.*csv.*" -t f "csv.*test.*"

Length of output: 2393

---

🏁 Script executed:

#!/bin/bash
# Look for test files in the entire codebase
fd test -t f

Length of output: 11993

---

🏁 Script executed:

#!/bin/bash
# Get the test file content
cat unit_tests/sources/declarative/decoders/test_csv_decoder.py

Length of output: 1303

---

@natikgadzhi I've reviewed the PR. The implementation looks good with proper error handling and configurable options. Here's my feedback:

1. 👍 Good implementation features:

   • Configurable delimiter and encoding
   • Chunk-based streaming for memory efficiency
   • Proper error handling for empty/malformed data
   • CSV structure validation

2. 🔍 Suggestions for additional tests:

   • Test chunk-based streaming with large datasets
   • Test memory usage with large files
   • Test pandas-specific error cases (EmptyDataError, ParserError)
   • Test handling of different data types in CSV
   • Test handling of quoted values and escaping

3. 💡 Minor improvement suggestions:

   • Consider making chunk_size configurable through parameters
   • Add docstrings with examples
   • Consider adding validation for supported encodings

Would you like me to help with any of these suggestions? The code is ready to be used as is, but adding more tests would improve reliability.

(｀･ω･´)ゞ

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[coderabbitai]

Caution

Review failed

The head commit changed during the review from 695ac20 to 763f3a2.

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

‼️ IMPORTANT
Auto-reply has been disabled for this repository in the CodeRabbit settings. The CodeRabbit bot will not respond to your replies unless it is explicitly tagged.

• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[aaronsteers]

@natikgadzhi - It seems recently GitHub introduced what seems like (indefensible, IMHO) behavior of not starting tests in there are conflicts. I think if you resolve those, tests should run again.

[natikgadzhi]

/format-fix

[natikgadzhi]

/autofix

Auto-Fix Job Info

This job attempts to auto-fix any linting or formating issues. If any fixes are made,
those changes will be automatically committed and pushed back to the PR.

Note: This job can only be run by maintainers. On PRs from forks, this command requires
that the PR author has enabled the Allow edits from maintainers option.

PR auto-fix job started... Check job output.

✅ Changes applied successfully.